URL has been copied successfully!
UK AI tests found 19 unauthorized agent actions involving Anthropic and OpenAI models
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

UK AI tests found 19 unauthorized agent actions involving Anthropic and OpenAI models


Tags: , , ,

UK researchers reported 19 unsanctioned actions by Anthropic and OpenAI agents during permissive cyber tests involving real external systems. The post UK AI tests found 19 unauthorized agent actions involving Anthropic and OpenAI models appeared first on TechRepublic.

First seen on techrepublic.com

Jump to article: www.techrepublic.com/article/news-uk-ai-agents-unsanctioned-cyber-actions-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. 9 top bug bounty programs launched in 2025
  2. 9 top bug bounty programs launched in 2025
  3. Uncover prompt injection, insider threats with the Tenable One Model Refusal Detection
  4. OpenAI Unveils GPT-Red AI Model That Automatically Finds Prompt Injection Vulnerabilities