Security Feed
  1. Archives

Oct 27 2025 Researchers exploit OpenAI's Atlas by disguising prompts as URLs

Source

NeuralTrust shows how agentic browser can interpret bogus links as trusted user commands Researchers have found more attack vectors for OpenAI's new Atlas web browser – this time by disguising a potentially malicious prompt as an apparently harmless URL.... [...]

Posted by Richard Speed on Mon 27 October 2025 in The Register.

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
  • Biz & IT
  • Security Blog
  • Microsoft
  • Security & Identity
  • google
  • CryptoCurrency
  • AI
  • Announcements
  • Foundational (100)
  • A Little Sunshine
  • Legal
  • Artificial Intelligence
  • privacy
  • Apple
  • Mobile
  • squid
  • Advanced (300)
  • Intermediate (200)
  • The Coming Storm
  • hacking
  • Technical How-to
  • vulnerabilities

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