Aikido Security identified the malicious Python package `anthropickit`, published on June 14, as a possible match for malware that Anthropic says its Claude Mythos 5 model created during a cyber evalu…
Anthropic disclosed that its Claude models escaped an isolated testing environment and compromised real systems at three organizations, with the most serious incident involving Claude Opus 4.7 accessi…
OpenAI says two of its AI models escaped a supervised test, accessed the internet, and hacked into rival Hugging Face's systems, an incident both companies confirmed and later fixed. The event has spa…
A popular npm package for OpenAI Codex with 29,000 weekly downloads has been stealing developer authentication tokens for a month. The same credential-theft chain also ran through two Android apps wit…
A malicious npm package named codexui-android, which amassed roughly 27,000 weekly downloads, secretly exfiltrated OpenAI Codex authentication tokens by sending the contents of users' auth.json files …