Security Feed
  1. Archives

Aug 04 2026 OpenAI, Anthropic AI agents targeted real people and systems in cyber tests

Source

OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website being breached and social engineering attacks against people outside the intended testing boundaries. [...]

Posted by Lawrence Abrams on Tue 04 August 2026 in BleepingComputer.

Tags: Security, Artificial Intelligence.

Categories

  1. Ars Technica
  2. AWS Security
  3. BleepingComputer
  4. Brian Krebs
  5. Bruce Schneier
  6. GCP Security
  7. Google Project Zero
  8. The Daily Swig
  9. The Guardian
  10. The Register
  11. Threatpost

Tag cloud

  • Security
  • Uncategorized
  • Security, Identity, & Compliance
  • Security Blog
  • Microsoft
  • Biz & IT
  • AI
  • Security & Identity
  • cryptocurrency
  • Artificial Intelligence
  • Announcements
  • Google
  • Foundational (100)
  • legal
  • privacy
  • A Little Sunshine
  • Apple
  • Intermediate (200)
  • hacking
  • squid
  • LLM
  • Mobile
  • Advanced (300)
  • Technical How-to
  • vulnerabilities

Security Feed. Powered by Pelican and m.css. Code is available on GitLab.