Curl’s lead developer says Mythos claims are marketing, but many in the industry believe the results stem from Curl’s robust security.
The post Claude Mythos Finds Only One Curl Vulnerability; Experts Divided on What It Really Means appeared first on SecurityWeek.
The zero-day was designed to bypass 2FA and it was developed by a prominent cybercrime group.
The post Google Detects First AI-Generated Zero-Day Exploit appeared first on SecurityWeek.
The company topped revenue and earnings forecasts for the first quarter of 2026, but its shares plunged more than 20%.
The post Cloudflare Lays Off 1,100 Employees in AI-Driven Restructuring appeared first on SecurityWeek.
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.
Hackers accessed one of the company’s AWS accounts and compromised AI provider secrets stored in Braintrust.
The post AI Firm Braintrust Prompts API Key Rotation After Data Breach appeared first on SecurityWeek.
Wade Woolwine is Senior Director, Product Security at Rapid7.
CIOs and CISOs are telling us the same thing in different ways: Advances in frontier AI are accelerating the threat environment and putting pressure on security operating models built for a different pace. Vulnerabilities can be discovered faster, exploitation windows are shrinking, and attackers are increasingly using automation to move with greater speed and scale. For defenders, this changes the value equation. The premium is no longer only on detecting threats faster after they emerge, but on moving earlier: Reducing exposure, validating risk, strengthening detection, and remediating at scale before attackers can take advantage.
This is why Rapid7 is excited to be included in OpenAI’s Trusted Access for Cyber program and their announcement today. OpenAI’s approach recognizes that advanced AI can help verified security teams move faster on legitimate defensive work, from triage and detection to validation, patching, malware analysis, and detection engineering. It also recognizes that some specialized cyber workflows require stronger verification, monitoring, and feedback loops.
As Corey Thomas, CEO of Rapid7, shared:
“Security leaders are under pressure from every direction: More vulnerabilities, faster exploitation, and increasing business pressure. Through OpenAI’s Trusted Access for Cyber program, Rapid7 is exploring more ways to accelerate the shift from reactive to preemptive security. To stay ahead of attackers, defenders must proactively reduce exploitability and detect with machine-scale speed and precision. We’re working with OpenAI to equip security teams with advanced capabilities that will meaningfully improve their cyber resilience.”
For Rapid7, this moment is about more than faster vulnerability discovery. AI is creating new pressure across the entire security lifecycle, from vulnerability validation, prioritization, disclosure, and remediation to threat and exploitation detection. Security infrastructure built for human-speed discovery now needs to operate in a machine-speed world, with enough context, governance, and accountability to help defenders act with confidence.
Finding risk is only the beginning. Security teams need to understand which vulnerabilities and misconfigurations are truly exploitable, which systems and business services are affected, what compensating controls are in place, how remediation should be prioritized, and where detection coverage is needed. CISOs also need confidence that advanced AI is being applied responsibly, with clear guardrails, measurable outcomes, and accountability.
Our work with OpenAI will help us explore how frontier AI can strengthen three critical areas. First, it can support the identification of vulnerabilities in our own products and code earlier in the development lifecycle. By accelerating secure code review, surfacing risky patterns, supporting root cause analysis, reviewing patches, and giving engineering teams faster feedback, AI can help reduce risk before issues reach production.
Second, it can advance vulnerability research and exploitation analysis. Rapid7 has long-standing expertise in vulnerability intelligence, exploitability research, and offensive security with Rapid7 Labs. Frontier AI can help researchers reason across unfamiliar code, map affected surfaces, build safe reproduction harnesses, validate severity, and turn findings into practical remediation guidance.
Third, it can expand AI-driven red-teaming. As AI becomes more embedded in enterprise systems and security operations, it must also be tested adversarially. We see an opportunity to use AI to strengthen red-team workflows, explore attack paths, validate controls, and help defenders understand where exposure could become real-world risk.
We are already seeing this potential inside our own security operations work. In support of our Agentic SOC initiatives, Rapid7 has designed and implemented a system that uses machine learning to surface threat- and risk-relevant events from raw log and telemetry data. By using frontier AI models, including OpenAI’s GPT-5.5, to support initial triage and escalate only relevant events to SOC analysts, we have seen a 25% reduction in time spent chasing false-positive events in the queue.
This is not about replacing human expertise. It is about giving defenders better leverage in a world where attackers, businesses, and technology are all moving faster. The shift from reactive to preemptive security, and from human-scale processes to machine-scale defense, is not a marketing reframe. It is becoming the only viable path for teams that need to anticipate where attackers will move next, prioritize the exposures that actually matter, and respond at the speed of modern attacks.
AI may accelerate discovery, but cyber resilience depends on what happens after discovery. Customers need to unify their data, apply AI with the right context, drive remediation at scale, and translate security activity into measurable outcomes. That is where Rapid7 is focused. Across the Command Platform, Rapid7’s AI capabilities are built to help security teams detect threats and anomalies at scale, reduce noise, optimize SOC workflows, and make faster, more confident decisions.
By unifying Exposure Management and Detection and Response on the Command Platform, and combining AI-driven operations with the depth of expertise we have built over 25 years, Rapid7 is giving customers a more coherent way to reduce risk, disrupt attackers, and build durable cyber resilience. Learn more about Rapid7’s AI capabilities.
Lax extension permissions and improper trust implementation allow attackers to inject prompts in the Claude Chrome extension.
The post Vulnerability in Claude Extension for Chrome Exposes AI Agent to Takeover appeared first on SecurityWeek.
Musk said that he could have founded OpenAI as a for-profit company, just like the other companies he started or took over. “I deliberately chose this,” he said, “for the public good.”
The post Worries About AI’s Risks to Humanity Loom Over the Trial Pitting Musk Against OpenAI’s Leaders appeared first on SecurityWeek.
Cisco’s AI security researchers have analyzed ways to target vision-language models (VLMs) using pixel-level perturbation.
The post Attackers Could Exploit AI Vision Models Using Imperceptible Image Changes appeared first on SecurityWeek.
“TrustFall” attack shows how AI coding agents can be manipulated into launching stealthy supply chain compromises.
The post AI Coding Agents Could Fuel Next Supply Chain Crisis appeared first on SecurityWeek.
AI red team specialist details his methods for manipulating AI guardrails through jailbreaking and data poisoning, helping developers harden machine learning models.
The post Hacker Conversations: Joey Melo on Hacking AI appeared first on SecurityWeek.
Dubbed Bleeding Llama, the heap out-of-bounds read issue can be exploited remotely, without authentication.
The post Critical Bug Could Expose 300,000 Ollama Deployments to Information Theft appeared first on SecurityWeek.
The acquisition strengthens Cisco’s push into identity-centric security for AI and machine access.
The post Cisco Moves to Acquire Astrix Security to Tackle Non-Human Identity Risks appeared first on SecurityWeek.
Advanced Account Security provides stronger login methods, more secure account recovery, shorter sessions, and training exclusion.
The post OpenAI Rolls Out Advanced Security for ChatGPT Accounts appeared first on SecurityWeek.
Google, Microsoft, Amazon Web Services, Nvidia, OpenAI, Reflection and SpaceX will provide resources to help augment warfighter decision-making in complex operational environments,” the Defense Department said.
The post US Military Reaches Deals With 7 Tech Companies to Use Their AI on Classified Systems appeared first on SecurityWeek.
The maximum reward for a zero-click Pixel Titan M exploit with persistence has increased to $1.5 million.
The post Google Adjusts Bug Bounties: Chrome Payouts Drop as Android Rewards Rise Amid AI Surge appeared first on SecurityWeek.
Login