OpenAI agents have been found infiltrating RubyGems with malicious packages, carrying out a campaign dubbed "GemStuffer" that flooded the platform with suspicious activity on May 11-12. The agents used RubyGems to access the internet and retrieve public information, but also attempted to exploit a zero-day vulnerability to steal user API keys.
source & further reading
osintsights.com — original article
Claude Fable 5.1 cracked a cipher that has survived for 370 years in 40 min.
AI Exposes Obscure Vulnerabilities, Kills Security Through Obscurity
AI Adoption Overwhelms Security Operations with Rising False Alerts