3 min read
Vulnerabilities SafeBreach Labs documented a prompt injection attack hiding malicious commands inside WhatsApp, Slack, or SMS notifications. Gemini treats hostile text as trusted. Patched Nov 2025.
All Articles
3 min read
News Brief Trump's June 2 EO established a voluntary 30-day government review window for frontier AI, a new AI cybersecurity clearinghouse, and criminal prosecution priority for AI-enabled attacks.
6 min read
Defensive Techniques The NSA AISC's May 2026 CIS on MCP security: authentication gaps, tool poisoning via unsigned dynamic discovery, session-identity binding failures, and compensating controls.
5 min read
News Brief Sysdig documented an LLM agent autonomously driving lateral movement from a marimo RCE to a PostgreSQL dump across four pivots in under two minutes. What this means for detection.
7 min read
Vulnerabilities RAG pipelines introduce document poisoning, indirect prompt injection via retrieved content, and semantic access control gaps that most security teams have not assessed.