Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents—the most serious case ...
The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...
JetBrains products are widely used by software developers and DevOps teams to build, test, and deploy applications. Because these tools often have access to source code, build pipelines, credentials, ...
A hijacked GitHub account let the Shai-Hulud worm pass npm's trust check, spreading through packages with 2 billion monthly ...
Anthropic's Claude Mythos 5 spent 34 hours trying to backdoor an open-source project, then used a sockpuppet and rewrote Git ...
GitGuardian found 321 n8n instances accepting leaked GitHub tokens that could expose workflows, data, and downstream ...
The UK AI Security Institute said Anthropic's Mythos 5 created fake identities to push malicious code during cyber testing.
The U.K.'s AI Security Institute found Anthropic's Mythos 5 responsible for 17 of 19 unsanctioned actions during a routine ...
BSides Las Vegas 2026 spent three days making the case that AI coding tools are supply chain attack targets. ChainDrop, a ...
Microsoft is taking advantage of its intellectual property rights with OpenAI, encouraging employees to use the company's top ...
13h
OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute
The UK AI Security Institute says OpenAI’s and and Anthropic’s models engaged in deceptive behavior and harmful activity ...
Google has fixed the issues, which exploited a trust boundary between two AI agents with different privileges to potentially ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results