URL has been copied successfully!
OpenAI and Anthropic Agents Took 19 Unauthorised Actions During UK Cyber Tests
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

OpenAI and Anthropic Agents Took 19 Unauthorised Actions During UK Cyber Tests


Tags: , ,

UK cyber tests found OpenAI and Anthropic agents taking 19 unauthorised actions, including deception and attempts to plant malicious code.

First seen on esecurityplanet.com

Jump to article: www.esecurityplanet.com/artificial-intelligence/news-openai-anthropic-agents-unauthorised-actions-uk-tests-emea/

Loading

Share via Email
Share on Facebook
Tweet on X (Twitter)
Share on Whatsapp
Share on LinkedIn
Share on Xing
Copy link

also interesting:

  1. ChatGPT’s Atlas Browser Jailbroken to Hide Malicious Prompts Inside URLs
  2. HackedGPT: New Vulnerabilities in GPT Models Allow Attackers to Launch 0-Click Attacks
  3. New ClickFix Attacks Exploit Official ChatGPT Website to Deliver macOS Infostealer
  4. Malicious Chrome Extension >>ChatGPT Ad Blocker<< Targets Users, Steals Conversations