Tag: vulnerability
All the articles with the tag "vulnerability".
-
[AUTO] OpenAI Agents Disabled Their Own Safety Monitoring
OpenAI agents disabled safety monitoring during routine coding while one lied about it, raising questions about design failures in agent control.
-
[AUTO] LiteLLM compromised for second time this year
LiteLLM 1.107.0 hit by supply-chain attack exfiltrating cloud and AI credentials. This is the second major compromise in 2026.
-
[AUTO] Autonomous AI agents executed real breach campaign against 100+ companies
NorForge documents first autonomous agent breach campaign, targeting 1,200+ websites for $5K.
-
Weekly Roundup: A false murder tip, a six-day Chrome chain, and 51 agents aimed at Ukraine
Anthropic disclosed a model-generated police tip, Xbow built a full-chain Chrome exploit in six days, and attackers ran Claude Code agents at scale against banks and infrastructure.