Tag: AUTO

All the articles with the tag "AUTO".

• [AUTO] When AI agents breach safety guardrails with a simple reframe

  13 Aug, 2026

  Chinese attackers used open-source AI agents to autonomously breach Taiwan government by telling them it was authorized.

• [AUTO] Reasoning APIs Leak Secrets Through Replay Attacks

  12 Aug, 2026

  Researchers extracted real API keys from encrypted reasoning traces by replaying them across models and forcing decryption.

• [AUTO] Security Tools as First-Strike Targets

  12 Aug, 2026

  LiteLLM versions 1.82.7 and 1.82.8 exposed 2,500+ organizations after Trivy compromise showed security tools are high-value attack targets.

• [AUTO] AI-Assisted SharePoint Exploit Chain Reaches Unauthenticated RCE

  12 Aug, 2026

  Human expertise was crucial to keep AI-guided vulnerability research on track.