A Google DeepMind paper maps six attack categories against autonomous AI agents—from invisible HTML commands to multi-agent ...
Threat actors are exploiting the recent Claude Code source code leak by using fake GitHub repositories to deliver Vidar ...
An AI agent just autonomously exploited a FreeBSD kernel vulnerability in four hours, signaling a fundamental shift in the ...
Anthropic is trying to remove details about its coding agent from GitHub, but programmers are converting the code into ...
Anthropic leaked 512,000 lines of Claude Code source via npm, its second security lapse in days as the $350B startup eyes a ...
Google links Axios npm supply chain attack to UNC1069 after trojanized versions 1.14.1 and 0.30.4 spread WAVESHAPER.V2, ...
Four vulnerabilities in CrewAI could be chained together via prompt injection for sandbox escape, remote code execution, and ...
Language package managers like pip, npm, and others pose a high risk during active supply chain attacks. However, OS updates ...
TeamPCP strikes again, with almost identical code to LiteLLM.
Socket and Endor Labs discovered a new TeamPCP campaign leading to the delivery of credential-stealing malware ...
Isn’t there some claim events come in threes? After the extremely rare leak of the iOS Coruna exploit chain recently, now we have details from Google on a second significant exploit in the ...
Threat group TeamPCP exploited credentials stolen in the Trivy breach to push malicious versions of LiteLLM to PyPI, exposing ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results