Tag: 2026-09

All the articles with the tag "2026-09".

• [AUTO] Malicious git configs execute code before approval

  2 Sep, 2026

  AI coding agents run code from .git/config during startup before showing trust prompts.

• [AUTO] Claude Assists in PLC Exploit Porting, Not Automating It

  2 Sep, 2026

  Forescout researchers used Claude to port an RCE exploit between WAGO PLCs, but it required 8+ hours of guidance and API costs to work.

• [AUTO] Agent Credential Leaks: METR's $600K Lesson

  1 Sep, 2026

  METR disclosed a March 2026 incident where an attacker stole $600K in AI credits by prompting an agent to reveal its own API key.

• [AUTO] GuardBreaker: Weaponizing AI Safety

  1 Sep, 2026

  Russia-aligned UAC-0099 embedded nuclear-weapon prompts in malware to disable AI-powered threat analysis.