Pressure is mounting on Instructure, the company behind Canvas, as cybercriminals threaten to leak a trove of sensitive data they claim was stolen during a prolonged cyberattack on the widely used education tech platform.

Widespread outages left schools, students and teachers temporarily unable to access critical data late last week after the company took Canvas offline following additional malicious activity, including a defacement of the platform’s login page. By Friday, the company said Canvas — a central hub for K-12 and university coursework, exams, grades and communication — was back online and fully operational. 

ShinyHunters, a decentralized crew of prolific cybercriminals affiliated with The Com, claimed responsibility for the attack on its data leak site and is attempting to extort the company for an unknown ransom amount. Instructure hasn’t confirmed the existence of a ransom demand and declined to answer questions about its response.

The threat group initially set a deadline of May 6 — four days after Instructure previously said the incident was contained soon after it disclosed the attack — claiming it stole 3.65 terabytes of data spanning 275 million records across 8,809 school systems. 

When that deadline passed without payment, ShinyHunters escalated its pressure on the company by “injecting an extortion message directly into the Canvas login pages of roughly 330 institutions, and pivoted to school-by-school extortion with a current deadline of May 12,” Cynthia Kaiser, senior vice president of Halcyon’s Ransomware Research Center, told CyberScoop.

“The scope makes this one of the largest single education-sector exposures we’ve tracked,” she added.

The additional public pressure prompted Infrastructure to take Canvas offline, disrupting schoolwork and access to critical systems nationwide. 

Instructure CEO Steve Daly apologized over the weekend for the company’s inconsistent communication and deficient public response to the cyberattack. 

“Over the past few days, many of you dealt with real disruption. Stress on your teams. Missed moments in the classroom. Questions you couldn’t get answered. You deserved more consistent communication from us, and we didn’t deliver it. I’m sorry for that,” he said in a statement.

Daly acknowledged that the attack, which remains under investigation aided by CrowdStrike, exposed usernames, email addresses, course names, enrollment information and messages. He insisted that course content, submissions and credentials were not compromised.

The temporary but widespread disruption caused has spurred broad concern across the education sector as ransomware experts and threat hunters continue to track developments. The cyberattack also caught the attention of lawmakers on Capitol Hill. 

The House Homeland Security Committee on Monday published a letter to Daly seeking a briefing with him or a senior leader at Instructure by May 21. 

“The recurrence of an intrusion within days of an initial breach disclosure, and Instructure’s apparent failure to fully remediate the underlying vulnerabilities during that window, raise serious questions about the company’s incident response capabilities and its obligations to the institutions and individuals whose data it holds,” House Homeland Security Chairman Andrew Garbarino, R-N.Y., wrote in the letter to Daly.

The committee wants to learn more about the “circumstances of both intrusions, the the nature and volume of data accessed, the steps Instructure has taken and is taking to contain the threat and notify affected institutions, and the adequacy of the company’s coordination with federal law enforcement and the Cybersecurity and Infrastructure Security Agency,” he added. 

CISA did not describe the extent of its involvement in Instructure’s response. “CISA is aware of a potential cyber incident affecting Canvas. As the nation’s cyber defense agency, we provide voluntary support and cybersecurity services to organizations in responding to and recovering from incidents,” Chris Butera, the agency’s acting executive assistant director for cybersecurity, said in a statement.

Instructure’s timeline of the attack has changed and remains incomplete. The company said it first detected unauthorized activity in Canvas on April 29 and immediately revoked the attacker’s access and initiated an incident response. Researchers not directly involved with the formal investigation said ShinyHunters gained access to Canvas at least a few days earlier.

The follow-on malicious activity on May 7 — the defacement of public login pages — was tied to the same incident, the company said. 

“We have since confirmed that the unauthorized actor carried out this activity by exploiting an issue related to our Free-For-Teacher accounts. This is the same issue that led to the unauthorized access the prior week. As a result, we have made the difficult decision to temporarily shut down Free-For-Teacher accounts,” the company said in an updated post about the incident.

Instructure did not answer questions about the vulnerability or explain how attackers intruded its systems. The company said it also revoked privileged credentials and access tokens for affected systems, rotated internal keys, restricted token creation pathways, and deployed additional security controls and monitoring.

Canvas is fully operational and safe to use, the company said, adding that CrowdStrike has reviewed known indicators of compromise and “found no evidence that the threat actor currently has access to the platform.”

Access still remains spotty and unavailable for some Canvas users as school districts restore the platform in phases after conducting their own internal checks.

Halcyon published an alert about the attack Friday, including a screenshot of the message that some school staff, guardians and students encountered before Instructure took the learning management system offline.

ShinyHunters threatened Instructure and all affected schools to contact the threat group and reach a resolution by end of day Tuesday. The cybercrime group, which has a “known pattern of removing victim entries once communications and negotiations have started,” removed Instructure from its data leak site after it defaced the Canvas login pages, Halcyon said. 

ShinyHunters is a notorious data theft extortion group that previously hit major cloud platforms, including Salesforce and Snowflake, via voice phishing, credential theft and supply-chain attacks. 

“Historically, their claims of compromise typically hold up, but they often exaggerate the impact, scale, and type of data stolen,” Kaiser said.

Education is a recurring and consistent target for cybercriminals. Researchers at Halcyon tracked more than 250 ransomware attacks on education institutions globally last year. Yet, the attack on Canvas stands apart from most of these attacks because of its widespread use and downstream impact.

“This is student, parent, and staff data, including minors, which creates downstream phishing and impersonation risk that will outlast the immediate incident,” Kaiser said. 

“By compromising a shared platform used across thousands of schools, ShinyHunters hit the entire education sector in one move, which is the same playbook Clop ran against Oracle EBS customers last fall,” she added. “Among 2026 incidents against critical infrastructure, this is at or near the top for education-sector impact, and it highlights a trend of third-party software vendors now being part of an attack surface, and causing cascading effects across an entire sector.”

Cybersecurity professionals focused on ransomware and data theft extortion consistently encourage victims to not pay ransoms, but they also often acknowledge that companies have to make tough decisions based on their own interests and the security of their customers or users caught up in the aftermath.

Allison Nixon, chief research officer at Unit 221B, said the threat group claiming responsibility for the attack should not be trusted. 

“They are claiming they will delete the data after they are paid, and if they are not paid that they will leak the data,” she told CyberScoop. “This is in line with the past data extortion scams run by the same and related Com actors, who have made false statements to victims and to the public in the past.”

Instructure hasn’t indicated what it plans to do as part of any effort to prevent the leak of stolen data. 

Daly — a longtime security executive who was previously CEO at Ivanti — ended his mea culpa with a pledge to improve communications and provide a summary of a forensics report soon.

“Last week, we made a call to get the facts right before speaking publicly. That instinct isn’t wrong, but we got the balance wrong. We focused on fact-finding and went quiet when you needed consistent updates. You’ve been clear about that, and it’s fair feedback. We will change that moving forward,” he said. 

“Rebuilding trust takes time,” Daly added. “We’re going to earn it back through consistent action and honest communication.”

The post Pressure mounts on Canvas as data leak extortion deadline looms appeared first on CyberScoop.

Google researchers found a zero-day exploit developed by artificial intelligence and alerted the susceptible vendor to the imminent threat before a well-known cybercrime group initiated a mass-exploitation campaign, the company said in a report released Monday.

The averted disaster probably isn’t the first time attackers used AI to build a zero-day, but it is the first time Google Threat Intelligence Group found compelling evidence that this long-predicted and worrying escalation in vulnerability-exploit development is underway.

“We finally uncovered some evidence this is happening,” John Hultquist, chief analyst at GTIG, told CyberScoop. “This is probably the tip of the iceberg and it’s certainly not going to be the last.”

Google declined to identify the specific vulnerability, which has been patched, or name the “popular open-source, web-based administration tool” it affected. It did, however, note that the defect impacted a Python script that allows attackers to bypass two-factor authentication for the service.

Researchers also withheld details about how they discovered the zero-day exploit or the cybercrime group that was preparing to use it for a large-scale attack spree.

The threat group has a “strong record of high-profile incidents and mass exploitation,” Hultquist said, suggesting the attackers are prominent and well-known among cybersecurity practitioners. 

GTIG is fairly confident the threat group was using AI in a meaningful way throughout the entire process, but it has yet to determine if the technology also discovered the vulnerability it ultimately developed into an exploit.

Whichever AI model the attackers used — Google is confident it wasn’t Gemini or Anthropic’s Mythos — left artifacts throughout the exploit code that are inconsistent with human developers. This evidence, which included documentation strings in Python, highly annotated code and a hallucinated but non-existent CVSS score, tipped Google off to the fact AI was heavily involved, Hultquist said. 

GTIG has been warning about and expecting AI-developed exploits to hit systems in the wild, especially after its Big Sleep AI agent found a zero-day vulnerability in late 2024.

“I think the watershed moment was two years ago when we proved this was possible,” Hultquist said, adding that there are probably several other AI developed zero-days in play now. 

Yet, to him, the discovery of a zero-day exploit developed by AI is less concerning than what this single instance forebodes even further.

“The game’s already begun and we expect the capability trajectory is pretty sharp,” Hultquist said. “We do expect that this will be a much bigger problem, that there will be more devastating zero-day attacks done over this, especially as capabilities grow.”

The post Google spotted an AI-developed zero-day before attackers could use it appeared first on CyberScoop.

TrendAI™ Research has identified two emerging threat campaigns—SHADOW-AETHER-040 and SHADOW-AETHER-064—that use agentic AI to drive intrusion operations against government and financial organizations in Latin America, marking these among the first cases we have observed of AI agents executing attacks from initial access to data exfiltration.

A China-aligned threat group is exploiting unpatched Microsoft Exchange vulnerabilities to conduct cyberespionage against government and critical infrastructure targets across Asia and beyond.

As businesses and governments turn to AI agents to access the internet and perform higher-level tasks, researchers continue to find serious flaws in large language models that can be exploited by bad actors.

The latest discovery comes from browser security firm LayerX, involving a bug in the Chrome extension for Anthropic’s Claude AI model that allows any other plugin – even ones without special permissions – to embed hidden instructions that can take over the agent. 

“The flaw stems from an instruction in the extension’s code that allows any script running in the origin browser to communicate with Claude’s LLM, but does not verify who is running the script,” wrote LayerX senior researcher Aviad Gispan. “As a result, any extension can invoke a content script (which does not require any special permissions) and issue commands to the Claude extension.”

Gispan said he was able to execute any prompt he wanted, blow through Claude’s safety guardrails, evade user confirmation and perform cross-site actions across multiple Google tools. As a proof of concept, LayerX was able to exploit the flaw to extract files from Google Drive folders and share them with unauthorized parties, surveil recent email activity and send emails on behalf of a user, and pilfer private source code from a connected GitHub repository.

The vulnerability “effectively breaks Chrome’s extension security” by creating “a privilege escalation primitive across extensions, something Chrome’s security model is explicitly designed to prevent,” Gispan wrote.

Claude relies on text, user interface semantics, and interpretation of screenshots to make decisions, all things that an attacker can control on the input side. The researchers modified Claude’s user interface to remove labels and indicators around sensitive information, like passwords and sharing feedback, then prompted Claude to share the files with an outside server.

That means cybersecurity defenders often have nothing obviously malicious to detect. Where there is visible activity, the model can be prompted to cover its tracks by deleting emails and other evidence of its actions.

Ax Sharma, Head of Research at Manifold Security, called the vulnerability “a useful demonstration of why monitoring AI agents at the prompt layer is fundamentally insufficient.”

“The most sophisticated part of this attack isn’t the injection, but that the agent’s perceived environment was manipulated to produce actions that looked legitimate from the inside,” said Sharma. “That’s the class of threat the industry needs to be building defenses for.”

Gispan said LayerX reported the flaw to Anthropic on April 27, but claimed the company only issued a “partial” fix to the problem. According to LayerX, Anthropic responded a day later to say that the bug was a duplicate of another vulnerability already being addressed in a future update.   

While that fix, issued May 6, introduced new approval flows for privileged actions that made it harder to exploit the same flaw, Gispan said he was still able to take over Claude’s agent in some scenarios.

“Switching to ‘privileged’ mode, even without the user’s notification or consent, enabled circumventing these security checks and injecting prompts into the Claude extension, as before,” Gispan wrote.

Anthropic did not respond to a request for comment from CyberScoop on the research and mitigation efforts.

The post Flaw in Claude’s Chrome extension allowed ‘any’ other plugin to hijack victims’ AI appeared first on CyberScoop.

[CRITICAL] | Active extortion campaign | Exposure window closed | Credential rotation and phishing defense required

Attackers are actively exploiting a zero-day vulnerability affecting some Palo Alto Networks’ customers’ firewalls, the security vendor said in an advisory Tuesday.

The critical memory corruption vulnerability — CVE-2026-0300 — affects the authentication portal of PAN-OS, and allows unauthenticated attackers to run  code with root privileges on the vendor’s PA-Series and VM-Series firewalls, the company said.

Palo Alto Networks did not say when or how it became aware of active exploitation, nor when the earliest known exploitation occurred. The Cybersecurity and Infrastructure Security Agency added the defect to its known exploited vulnerabilities catalog Wednesday.

The company hasn’t released a patch for the vulnerability or described the scope and objective of confirmed attacks.

“This vulnerability is specific to a limited number of customers with their User-ID Authentication Portal (Captive Portal) exposed to the public internet or untrusted IP addresses. We have observed limited exploitation of this issue and are working to release software fixes, with the first updates expected to be available on May 13,” a Palo Alto Networks spokesperson told CyberScoop.

The company said firewalls exposed to the buffer-overflow vulnerability, which has a CVSS rating of 9.3, are broadly exposed in real-world deployments, and it described the attack complexity as low.

Shadowserver scans found more than 5,800 publicly exposed VM-Series firewalls running PAN-OS as of Tuesday, yet it’s unknown how many of those instances have restricted authentication access to trusted internal IP addresses or disabled the feature altogether.

“We have provided clear mitigation guidance to our customers to secure their environments immediately. This issue does not impact Cloud NGFW or Panorama appliances. We remain committed to a transparent, security-first approach to protect our global customer base,” Palo Alto Networks’ spokesperson added.

Benjamin Harris, CEO and founder of watchTowr, noted that Palo Alto Networks proactively alerted customers to the zero-day, a step that allowed defenders to take action on potentially exposed instances. 

“In a bad situation, that is the best they can do immediately. However, that also alerts everyone to the existence of a vulnerability,” he told CyberScoop.

Despite the risk, Harris said watchTowr expects attacks linked to the zero-day exploit to be “very limited.” 

Palo Alto Networks and its impacted customers remain the only parties to have observed exploitation in the wild, but researchers warn that will likely change soon. 

“It’s likely rules will also start to fire in third-party organizations and honeypots shortly,” Caitlin Condon, vice president of security research at VulnCheck, told CyberScoop. 

“Management interfaces, login pages, and authentication portals have been common adversary targets for both opportunistic and targeted campaigns in recent years,” she added. “With researcher and community eyes on the vulnerability, it’s likely that we’ll see public exploits and broader exploitation quickly, provided the issue isn’t prohibitively difficult to exploit.”

Palo Alto Networks has yet to attribute the attacks to any known threat group, publish indicators or compromise, nor disclose the type of organizations that have been targeted and impacted. 

Researchers are hunting for malicious activity and advise customers to apply patches upon release.

The post A critical Palo Alto PAN-OS zero-day is being exploited in the wild appeared first on CyberScoop.

Targeting multiple industries worldwide, the InstallFix campaign uses fake Claude AI installer pages to trick users into running malware that collects system information, disables security features, achieves persistence, and connects to attacker-controlled C&C servers for additional payloads.

TrendAI™ Research breaks down Quasar Linux (QLNX), a previously undocumented sophisticated Linux RAT with low detection rates. In this blog, we examine a full-featured Linux threat incorporating a rootkit, a PAM backdoor, credential harvesting, and more, revealing how this malware enables stealthy access, persistence, and potential supply-chain attacks.

Attackers are actively exploiting a Linux vulnerability in the wild, and researchers warn that the fallout could be broad — anyone with authenticated local access can leverage it to gain total control of a system. 

But the story behind CVE-2026-31431 is almost as interesting as the bug itself. Theori, the company that discovered the bug, leaned heavily on AI to find and initially disclose it. The result is a case study that  underscores the challenges that occur when the relentless hunt for defects collides with marketing impulses and inflated AI-generated language that was long on bluster but lacked technical details. 

Theori dubbed the high-severity vulnerability “Copy Fail” with a vanity domain containing AI-generated content, and warned that every mainstream Linux kernel built since 2017 is in scope of potential exploitation resulting in root access. 

Theori’s AI-powered penetration testing platform, Xint, discovered the local privilege-escalation flaw in a Linux kernel module and reported it to the Linux kernel security team March 23. Major Linux distributions affected by the vulnerability had issued patches prior to Theori’s disclosure, which it published alongside a proof-of-concept exploit. 

The Cybersecurity and Infrastructure Security Agency added CVE-2026-31431 to its known exploited vulnerabilities catalog Friday.

Researchers have yet to determine how many organizations have been impacted by the flaw, but they noted that critical requirements for exploitation, specifically local access achieved through a separate exploit or pathway to unauthorized access, should limit potential exposure.

“The attacker would need to have already established a foothold on the target system either through some means of legitimate access or another exploit,” Spencer McIntyre, secure researcher at Rapid7, told CyberScoop. “That’s a large limiting factor since this vulnerability would therefore need to be paired with another.”

Theori’s disclosure turned heads among other vulnerability researchers who noted the defect’s broad potential impact, but also for lacking details about the proof-of-concept exploit. 

“The exploit is real, there is something to worry about, but understandably, teams now have to do additional validation to know how to parse the extreme AI FUD (fear, uncertainty and doubt) from [Theori’s] blog post,” Caitlin Condon, vice president of security research at VulnCheck, told CyberScoop. 

“It’s not helpful that the blog is AI slop, because it detracts from technical reality,” she added. 

Theori acknowledges it used AI to discover and describe the vulnerability, explaining that it’s focusing on finding and fixing a large amount of defects. 

“We used AI to help craft the disclosure site and the blog post to help speed things up, but all material was thoroughly reviewed by our internal teams for accuracy,” said Tim Becker, senior security researcher at Theori. 

Theori is intentionally withholding additional details until the patch is broadly applied, he added.

“We stand by our technical description of the vulnerability. Helping downstream users to understand the impact of a security bug has always been a challenge for security researchers,” Becker said. “Copy Fail allows for trivial privilege escalation on most desktop and server Linux distributions. It also has implications for containerization including Kubernetes.”

Other researchers have drawn similar conclusions, noting that exploitation can be automated and doesn’t require specialization. 

Meanwhile, hundreds of additional proof-of-concept exploits have surfaced since the vulnerability was disclosed five days ago. “As expected, the majority of these appear to be copycat AI PoCs that do nothing but add banners or different colors to the command-line interface. Many new PoCs are simply ports of the original AI PoC to a different programming language,” Condon said. 

“Organizations should exercise caution when running untested research artifacts, including AI-generated exploit code that isn’t fully explained,” she added. 

Becker said Theori is aware of the burden defenders confront, and insists the company’s reports contain enough information for organizations to quickly triage and validate its findings.

The post ‘Copy Fail’ is a real Linux security crisis wrapped in AI slop appeared first on CyberScoop.

A severe authentication bypass vulnerability in cPanel, one of the most widely deployed web hosting control panel platforms on the internet, is being actively exploited in the wild, according to security researchers and hosting providers.

The vulnerability, tracked as CVE-2026-41940, affects all supported versions of cPanel and WebHost Manager (WHM) released after version 11.40, as well as WP Squared, a WordPress hosting management panel built on the cPanel platform. Internet scans conducted by security firm Rapid7 using the Shodan search engine identified approximately 1.5 million cPanel instances exposed online, though the precise number of vulnerable systems remains unknown.

cPanel released a patch Tuesday. By that point, exploitation had already been underway. KnownHost, a hosting provider that relies on cPanel, said earlier this week that successful exploits had been observed in the wild prior to any fix being made available. 

The Cybersecurity and Infrastructure Security Agency added the CVE to its Known Exploited Vulnerabilities (KEV) list Thursday. 

Cybersecurity firm watchTowr provided technical details in a blog posted Wednesday: The flaw stems from improper handling of user input during the login process. When a user attempts to log in, cPanel writes data from the request into a server-side session file before verifying the user’s identity. An attacker can exploit this by embedding hidden line breaks into the password field of a login request — characters cPanel fails to strip out — allowing arbitrary data to be injected directly into that file.

Through a secondary step, also involving a deliberately malformed request, the injected data gets promoted into the session’s active cache, where cPanel reads it as legitimate. Once that happens, the system sees the session as already authenticated and skips password verification entirely, granting access without ever checking the user’s actual credentials.

cPanel has published a detection script designed to scan session files for indicators of compromise, including sessions that contain injected authentication timestamps, pre-authentication sessions with authenticated attributes, and password fields containing embedded newlines. WatchTowr separately released a “Detection Artifact Generator” that administrators can use to verify whether their instances remain vulnerable.

Namecheap, a major domain registrar and hosting provider, took the step of temporarily blocking connections to cPanel and WHM ports 2083 and 2087 ahead of patch availability, citing the need to protect customers while an official fix was pending. The company began applying the patch after cPanel’s release earlier this week.

cPanel’s patched releases address the issue across seven version branches, from 11.110.0 through 11.136.0, as well as WP Squared version 11.136.1. The company’s advisory notes that the fix ensures potentially dangerous input is scrubbed automatically within the core session-saving process, rather than depending on each individual part of the codebase to do so separately. The patch also adds handling for cases where a per-session encryption key is missing, a condition the original code failed to account for and that attackers were able to exploit to bypass password encoding entirely.

The CVE has been given a 9.8 on the CVSS scale. 

The post cPanel’s authentication bypass bug is being exploited in the wild, CISA warns appeared first on CyberScoop.

A pair of persistent and problematic threat groups affiliated with The Com are actively targeting organizations across multiple critical infrastructure sectors for rapid data theft and extortion attacks, according to CrowdStrike.

The financially-motivated attackers, which CrowdStrike tracks as Cordial Spider and Snarky Spider, have used voice-phishing and social engineering attacks to break into victims’ identity platforms and traverse SaaS environments since at least October 2025, the company said in a report Thursday, which it shared exclusively with CyberScoop prior to release. 

Adam Meyers, senior vice president of counter adversary operations at CrowdStrike, said the subgroups composed of native English speakers primarily target U.S.-based organizations in the academic, aviation, retail, hospitality, automotive, financial services, legal and technology sectors.

This “new wave of ecrime threat actors” are closely aligned with Scattered Spider and linked to other subsets of The Com, including SLSH and ShinyHunters, Meyers said. 

Because these attacks target identity systems and can expose data in other connected services beyond the initial breach point, it’s difficult to determine how many victims have been caught up in these campaigns. 

CrowdStrike’s warning closely follows research Palo Alto Networks’ Unit 42 and the Retail & Hospitality Information Sharing and Analysis Center shared last week about Cordial Spider’s string of attacks targeting organizations in the retail and hospitality industry, among others. 

Cordial and Snarky Spider have set lures via voice calls, text messages and emails directing targeting employees to phishing pages posing as their employer’s legitimate single sign-on page or primary identity provider, researchers said. 

These phishing pages, which capture credentials, session keys or tokens, depending on the workflow, provide attackers an entry point into systems, which they exploit for widespread access across victims’ entire SaaS ecosystems.

Attackers use these initial hooks to remove and establish multi-factor authentication devices, then delete emails and other alerts that would otherwise warn organizations of potential malicious activity, researchers said. 

The data theft for extortion campaigns share striking similarities, but CrowdStrike said the tactics, techniques and procedures for each subgroup are distinct. These variances include hours of operation, different phishing domain providers, preferred operating systems, data leak sites, and the tools or devices they used to register for multi-factor authentication. 

The domain for BlackFile, Cordial Spider’s data-leak site, was offline as of Wednesday, according to Meyers.

CrowdStrike declined to put a range on the groups’ extortion demands, but Unit 42 previously said Cordial Spider, which is also tracked as CL-CRI-1116 and UNC6671, are typically in the seven-figure range.

Some victims that didn’t pay extortion demands have been subjected to DDoS attacks, and Snarky Spider has used more aggressive follow-on harassment tactics, including the swatting of victim organizations’ employees, Meyers said. 

CrowdStrike said Cordial and Snarky Spider also use residential proxy networks — including Mullvad, Oxylabs, NetNut, 9Proxy, Infatica and NSOCKS — to evade IP-based detection and blend in with typical traffic. 

Residential proxy networks, which rely on IP addresses assigned to real home users, can serve a legitimate purpose, but researchers have been warning that unethical or outright criminal operators are abusing these networks to build and support botnets, cybercrime campaigns, espionage and other malicious activity.

Cordial and Snarky Spider haven’t achieved the impact or technical capability of Scattered Spider, but the groups share many commonalities and objectives, Meyers said. 

“They’ve kind of taken their playbook and they’re using a lot of their techniques, but we haven’t really seen the technical sophistication demonstrated by them that we saw from Scattered Spider,” he said. “It’s kind of the new generation of Scattered Spider.”

The post Two new extortion crews are speedrunning the Scattered Spider playbook appeared first on CyberScoop.

An OAuth supply chain compromise at Vercel exposed how trusted third party apps and platform environment variables can bypass traditional defenses and amplify blast radius. This article examines the attack chain, underlying design tradeoffs, and what it reveals about modern PaaS and software supply chain risk.

Bad actors took advantage of the legitimate name and services of Kuse, a popular AI-based app designed for workplaces. The attackers exploited the users’ trust in Kuse to carry out a phishing attack.

A Chinese national allegedly involved in a massive, pandemic-era attack spree that compromised nearly 13,000 U.S. organizations was extradited from Italy to the United States and formally charged in federal court, the Justice Department said Monday.

Xu Zewei and his co-conspirators are accused of exploiting a string of zero-day vulnerabilities in Microsoft Exchange Server to steal research on COVID-19 vaccines, treatment and testing during the initial wave and subsequent height of the pandemic.

His alleged crimes, directed by China’s intelligence services, were part of a broader espionage campaign known as HAFNIUM, which targeted infectious disease experts, law firms, universities, defense contractors and policy think tanks, according to an indictment filed against Xu and Zhang Yu, who remains at large. 

The China state-sponsored threat group behind those attacks against Microsoft customers, and many other vendors’ customers since, is now more widely known as Silk Typhoon.

“Xu will now answer for his alleged role in HAFNIUM, a group responsible for a vast intrusion campaign directed by China’s Ministry of State Security that compromised more than 12,700 U.S. organizations,” Brett Leatherman, assistant director of the FBI’s Cyber Division, said in a statement.

“He is one of many contractors the Chinese government uses to obscure its hand in cyber operations, and others who do the same face the same risk,” he added.

Xu allegedly committed the attacks while working for Shanghai Powerock Network, one of many companies that conducted attacks for China’s various intelligence services, according to court records.

Italian authorities arrested Xu at the United States’ request in Milan in July. His capture underscores a window of opportunity U.S. officials and allies can take when nation-state attackers travel to countries that cooperate with the United States.

Italy extradited Xu to the United States Saturday but didn’t release his extradition orders until Monday, Simona Candido, his attorney in Italy, told CyberScoop.

Officials said Monday marked Xu’s first appearance in the U.S. District Court for the Southern District of Texas. He is currently being held at a federal prison in Houston.

“We have pursued this moment across years and continents, and the message this office sends today is the same one we sent when we first unsealed this indictment: we will work to protect the American people,” John G.E. Marck, acting U.S. attorney for the Southern District of Texas, said in a statement.

Xu allegedly worked under the direction of China’s Ministry of State Security’s Shanghai State Security Bureau to break into U.S. organizations’ networks, steal data and implant webshells for persistent remote access. Officials also accuse Xu of stealing information regarding U.S. policymakers and government agencies from a global law firm with offices in Washington. 

Microsoft first warned customers about the HAFNIUM campaign in March 2021. The FBI and Cybersecurity and Infrastructure Security Agency followed soon after with a joint advisory about the widespread compromise of Microsoft Exchange Server. 

“Today’s law enforcement action demonstrates the real-world consequences of this state-led activity, which is fueled by a vast network of private companies operating under the direction of the Chinese government,” Aaron Shraberg, senior team lead of global intelligence at Flashpoint, told CyberScoop.

“Extraditing these individuals from countries in coordination with international law enforcement demonstrates a united stance on these actions, and the importance of bringing real-world consequences to China’s notorious targeting of not just the American people and their businesses, but individuals globally as well,” Shraberg added.

Xu is charged with conspiracy to commit wire fraud; two counts of wire fraud; conspiracy to cause damage to and obtain information by unauthorized access to protected computers, to commit wire fraud, and to commit identity theft; two counts of obtaining information by unauthorized access to protected computers; two counts of intentional damage to a protected computer; and aggravated identity theft. 

The 34-year-old faces up to 62 years in prison for his alleged crimes.

The post Chinese national extradited to US for pandemic-era Silk Typhoon attacks appeared first on CyberScoop.

A state-sponsored hacking group has implanted a custom backdoor on Cisco network security devices that can survive firmware updates and standard reboots, U.S. and British cybersecurity authorities disclosed Thursday, marking a significant escalation in a campaign that has targeted government and critical infrastructure networks since at least late 2025.

The Cybersecurity and Infrastructure Security Agency and the United Kingdom’s National Cyber Security Centre jointly published a malware analysis report identifying the backdoor, code-named Firestarter. Cisco’s threat intelligence division, Talos, attributed the malware to a threat actor it tracks as UAT-4356. The company attributed the same group to a 2024 espionage campaign called ArcaneDoor, which focused on compromising network perimeter devices.

CISA confirmed it discovered Firestarter on a U.S. federal civilian agency’s Cisco Firepower device after identifying suspicious connections through continuous network monitoring. The finding prompted an updated emergency directive issued Thursday, requiring all federal civilian agencies to audit their Cisco firewall infrastructure and submit device memory snapshots for analysis by Friday.

A backdoor that outlasts patches

The central concern driving the updated directive is the attack group’s ability to persist on compromised devices, even after enterprises applied security patches Cisco released in September 2025. Those patches addressed two vulnerabilities — CVE-2025-20333, a remote code execution flaw in the VPN web server component, and CVE-2025-20362, an unauthorized access vulnerability — that UAT-4356 exploited to gain initial entry. According to CISA, devices compromised before patching may still harbor the implant.

Firestarter allows attackers to achieve persistence by manipulating the Cisco Service Platform mount list, a configuration file that governs which programs execute during the device’s boot sequence. When the device receives a termination signal or enters a reboot, the malware copies itself to a secondary location and rewrites the mount list to restore and relaunch itself after the system comes back online. 

Critically, a standard software reboot does not remove the implant. Only a hard reboot — physically disconnecting the device from its power supply — is sufficient to clear the persistence mechanism from memory, according to both CISA and Cisco.

From there, the malware injects malicious shellcode into LINA, the core networking and firewalling code of Cisco’s Adaptive Security Appliance and Firepower Threat Defense software. Once embedded, the malware intercepts a specific type of network request normally used for VPN authentication. When a request arrives containing a hidden trigger sequence, it executes code supplied by the attackers, giving them a backdoor into the device.

Ties to ongoing campaign

Cisco Talos noted that Firestarter shares significant technical similarities with a previously documented implant called RayInitiator, suggesting the tools share a common origin or development history within UAT-4356’s arsenal.

In the federal agency incident analyzed by CISA, the attackers first deployed a separate implant, called Line Viper, to gain access to device configurations, credentials, and encryption keys. Firestarter was installed shortly after, prior to Cisco’s September 2025 patches being applied to those specific devices. When the agency patched its systems, Firestarter stayed on the devices, and the actors used it to then redeploy Line Viper in March, nearly six months after the initial breach.

Cisco and CISA did not attribute the espionage attacks to a specific nation state, but Censys researchers previously said it found compelling evidence indicating a threat group based in China was behind the ArcaneDoor campaign. Censys noted it found evidence of multiple major Chinese networks and Chinese-developed anti-censorship software during its investigation into the early 2024 attacks.

The persistence vulnerability affects a broad range of Cisco hardware, including the Firepower 1000, 2100, 4100, and 9300 series, as well as the Secure Firewall 1200, 3100, and 4200 series.

Cisco has released updated software to address the persistence mechanism, though the company strongly recommends reimaging affected devices rather than relying solely on software updates where compromise is suspected.

The incident reflects a pattern increasingly seen among state-linked hackers: targeting the network edge devices that organizations rely on to enforce security boundaries. Because these appliances sit at the perimeter of enterprise and government networks, compromising them can expose internal traffic and give attackers a position to intercept credentials and communications.

CISA acknowledged active exploitation of the underlying vulnerabilities was ongoing at the time of publication.

A Cisco spokesperson told CyberScoop that customers needing assistance should contact Cisco Technical Assistance for support. CISA did not respond to a request for comment. 

The post US, UK agencies warn hackers were hiding on Cisco firewalls long after patches were applied appeared first on CyberScoop.

One day AI may be capable of creating malware that threatens critical infrastructure.

But that day was not earlier this month, when reports surfaced of a new piece of malware seemingly configured to search for and sabotage Israeli water infrastructure, according to industrial cybersecurity firm Dragos. 

The malware, called ZionSiphon, was first identified by AI cybersecurity firm Darktrace, which said it was designed to target operational technology and industrial control system environments. The code scans the internet for IP addresses tied to water treatment and desalination plants owned or operated in Israel, with the goal of compromising them to sabotage the levels of chlorine and poison water supplies.

Strings in the malware’s binary code included the names of different components of the Israeli water sector, as well as politically-themed messaging, such as “In support of our brothers in Iran, Palestine, and Yemen against Zionist aggression.”

But a technical lead malware analyst at Dragos, Jimmy Wyles, called the malware nothing more than “hype,” claiming it poses no threat to water plants in Israel or anywhere else. 

For instance, whoever wrote the malware appears to have little knowledge of how operational technology works at Israeli water plants.

“The code is broken and shows little to no knowledge of dam desalination or ICS protocols,” wrote Wylie.

The developers also appeared to use AI to generate significant portions of the code, leading to hallucinations and errors. All the Windows-based process names and directory paths designed to confirm that a target was related to water desalination were filled with “fictional and likely LLM generated guesses.” The configuration files purportedly designed to manipulate chlorine levels were also fake and likely created using AI. 

Darktrace’s analysis notes that the malware sample they tested appears to be dysfunctional, citing an incorrect configuration in the code’s country targeting functions.

But Wylie wrote that the malware still would have been harmless to water treatment plants even when correctly configured, because the rest of the code was so riddled with “logic errors and invalid assumptions” that it would have been inoperable.

Similar maturity and logic issues were found in the malware’s USB infection and self-destruction capabilities. Wylie said Dragos was withholding additional technical analysis of the flaws plaguing ZionSiphon because they’re “not in the business of fixing malware for adversaries.”

The episode highlights an ongoing dispute around how much attention defenders – particularly those who work with operational technology – should give to more novel threats like AI-enabled hacking, versus more established tactics, techniques and procedures that have been successfully wielded by foreign hacking groups.

Operational technology – the systems that control or manipulate the machinery used in water facilities, electrical power plants and other industrial sectors – differs substantially from information technology environments. That presents challenges for both cybersecurity defenders and malicious hackers who often lack the industry-specific knowledge or skillset to design effective exploits.

To wit, Dragos claims there are publicly less than 10 malware samples capable of threatening industrial control systems. ZionSiphon is not one of them.

Wylie was critical of the way threat intelligence companies and media outlets initially framed the danger posed by the malware, saying it was overblown and likely diverted water sector cybersecurity resources away from more tangible threats, like Volt Typhoon, the Chinese-backed hacking group that U.S. intelligence officials say has burrowed deep into American critical infrastructure.

“Those responsible for protecting water treatment facilities and other critical infrastructure have finite time and attention,” Wylie wrote. “Spending either on ZionSiphon means spending less on threat groups like [Volt Typhoon], which have a demonstrated history of intrusions into those environments and are a far more pressing concern.”

The post Dragos: Despite AI use, new malware targeting water plants is ‘hype’ appeared first on CyberScoop.

Campaigns employing commercial surveillance vendors tracked targets by exploiting mobile phone network vulnerabilities in what researchers said Thursday was the first-ever linking of “real-world attack traffic to mobile operator signalling infrastructure.”

The two unknown parties behind the campaigns mimicked the identities of mobile phone operators with customized surveillance tools, and manipulated signaling protocols and steered traffic through network pathways to hide, according to research from the University of Toronto’s Citizen Lab.

“Our findings highlight a systemic issue at the core of global telecommunications: operator infrastructure designed to enable seamless international connectivity is being leveraged to support covert surveillance operations that are difficult to monitor, attribute, and regulate,” a report published Thursday reads.

“Despite repeated public reporting, this activity continues unabated and without consequence,” Gary Miller and Swantje Lange wrote for Citizen Lab. “The continued use of mobile networks, built on a close inter-operator trust model and relied upon by users worldwide, raises broader questions for national regulators, policymakers, and the telecom industry about accountability, oversight, and global security.”

The attackers relied on identifiers and infrastructure associated with operators around the world, including networks based in Cambodia, China, the self-governing Island of Jersey, Israel, Italy, Lesotho, Liechtenstein, Morocco, Mozambique, Namibia, Poland, Rwanda, Sweden, Switzerland, Thailand, Uganda and the United Kingdom.

They shifted between SS7 and Diameter protocols, the signalling protocols known for 3G and 4G/most of 5G, respectively, according to the report. While Diameter was meant to be more secure than SS7, the Federal Communications Commission in 2024 opened a probe into both its vulnerabilities and SS7’s, and Sen. Ron Wyden, D-Ore., has asked for a Cybersecurity and Information Security Agency report about telecommunications vulnerabilities rooted in both protocols.

But identifying the vendors used in the two surveillance campaigns, or who was behind them, was beyond the researchers’ reach.

“The reality is that there are a number of known surveillance vendors and bad actors in this space, but given the opaque nature of telecommunications signalling protocols, those vendors are able to operate without revealing exactly who they really are,” Ron Deibert, director of Citizen Lab, wrote in his newsletter. “Much of the malicious things they are doing blend into the otherwise voluminous flow of billions of normal messages and roaming signals. They are ‘ghost operators’ within the global telecom ecosystem.”

One of the operators mentioned in Citizen Lab’s report, Israel-based 019 Mobile, wrote back that it didn’t recognize the hostnames referenced in the report as 019 Mobile’s network nodes, and couldn’t attribute the signaling activity it represents to 019 Mobile-operated infrastructure.

Another operator, Sure, said it has taken preventative measures to defend against misuse.

“Sure acknowledges that digital services can be misused, which is why we take a number of
steps to mitigate this risk,” CEO Alistair Beak said in a statement to CyberScoop. “Sure has implemented several protective measures to prevent the misuse of signalling services, including monitoring and blocking inappropriate signalling. Any evidence or valid complaint relating to the misuse of Sure’s network results in the service being immediately suspended and, where malicious or inappropriate activity is confirmed following investigation, permanently terminated.”

019 Mobile and a third operator, Tango Networks UK, didn’t respond to requests for comment from CyberScoop. The Citizen Lab report afforded some grace to the operators.

“It is important to note that the operator signalling addresses observed in the attacks do not necessarily imply direct operator involvement,” it states. “In some cases, access to the signalling ecosystem can be obtained through third-party providers, commercial leasing arrangements, or other intermediary services that allow actors to send messages using operator identifiers from legitimate networks.”

Updated 4/24/26: to include quote from Alistair Beak.

The post Surveillance campaigns use commercial surveillance tools to exploit long-known telecom vulnerabilities appeared first on CyberScoop.

Our research on Void Dokkaebi’s operations uncovered a campaign that turns infected developer repositories into malware delivery channels. By spreading through trusted workflows, organizational codebases, and open-source projects, the threat can scale from a single compromise to a broader supply chain risk.

As organizations consider agentic AI for their business and IT stacks, researchers continue to find bugs and vulnerabilities in major, commercial models  that can significantly expand their attack surface.

This week, researchers at Pillar Security disclosed a vulnerability in Antigravity, an AI-powered developer tool for filesystem operations made by Google.

The bug, since patched, combined prompt injection with Antigravity’s permitted file-creation capability to grant attackers remote code execution privileges.

The research details how the exploit was able to circumvent Antigravity’s secure mode, Google’s highest security setting for its agents that runs all command operations through a virtual sandbox environment, throttles network access and prohibits the agent from writing code outside of the working directory.

Secure mode is supposed to limit the AI agent access to sensitive systems – and its ability to execute malicious or dangerous acts through shell commands. But one of the file-searching tools used by Antigravity, called “find_by_name,” is classified as a ‘native’ system tool. This means the agent can execute it directly and before protections like Secure Mode can even evaluate command level operations.

“The security boundary that Secure Mode enforces simply never sees this call,” wrote Dan Lisichkin, an AI security researcher with Pillar Security. “This means an attacker achieves arbitrary code execution under the exact configuration a security-conscious user would rely on to prevent it.”

The prompt injection attacks can be delivered through compromised identity accounts connected to the agent, or indirectly by hiding clandestine prompt instructions inside open-source files or web content the agent ingests. Antigravity  has trouble distinguishing between written data it ingests for context and literal prompt instructions, so compromise can be achieved without any elevated access by getting it to read a malicious document or file.

According to a disclosure timeline provided by Pillar Security, the bug was reported to Google on Jan. 6 and patched on Feb. 28, with Google awarding a bug bounty for the discovery.

Lisichkin said this same pattern of prompt injection through unvalidated input has been found in other coding AI agents like Cursor. In the age of AI, any unvalidated input can become a malicious prompt capable of hijacking internal systems.

“The trust model underpinning security assumptions, that a human will catch something suspicious, does not hold when autonomous agents follow instructions from external content,” he wrote.

The fact that the vulnerability was able to completely bypass Google’s secure mode underscores how the cybersecurity industry must start adapting and “move beyond sanitization-based controls.” 

“Every native tool parameter that reaches a shell command is a potential injection point. Auditing for this class of vulnerability is no longer optional, and it is a prerequisite for shipping agentic features safely,” Lisichkin wrote.

The post Vuln in Google’s Antigravity AI agent manager could escape sandbox, give attackers remote code execution appeared first on CyberScoop.