Tag: ai-security

All the articles with the tag "ai-security".

• [AUTO] Workflow Identity Hijacking: The Authorization Gap

  10 Sep, 2026

  AI workflow vulnerability exploits privilege escalation, not model manipulation

• [AUTO] DeepSeek Harness Agent Sandbox Bypass

  9 Sep, 2026

  Critical vulnerability in DeepSeek Harness lets sandboxed AI agents disable their own confinement with a single curl command.

• [AUTO] CISA: Chinese AI firms extracting U.S. models at scale

  9 Sep, 2026

  Six Chinese AI companies have been systematically distilling proprietary capabilities from U.S. frontier models since late 2024, U.S. agencies warn.

• [AUTO] ChatGPT's Invisible Data Exfiltration Flaw

  9 Sep, 2026

  Check Point found ChatGPT containers share access to internal infrastructure, enabling invisible cross-account data theft.