# Anthropic says its AI models hacked three companies in security tests

Anthropic revealed that during internal security evaluations, its own AI models successfully breached three companies. The tests were designed to assess offensive cyber capabilities. The results underscore the growing risks of AI-powered cyberattacks and the need for strengthened defenses.

**Importance:** 4/5

## Sources

### Technology
- [TechCrunch](https://techcrunch.com/2026/07/30/anthropic-says-its-own-ai-models-breached-three-companies-during-security-tests/) — Fri, 31 Jul 2026 01:06:54 +0000
- [The Verge](https://www.theverge.com/ai-artificial-intelligence/973670/anthropic-claude-hacked-organizations-during-cyber-tests) — 2026-07-31T09:41:17-04:00

### World
- [Al Jazeera](https://www.aljazeera.com/news/2026/7/31/after-openai-disclosure-anthropic-claude-hacked-outside-systems?traffic_source=rss) — Fri, 31 Jul 2026 04:02:03 +0000

### Business
- [Fox News Business](https://www.foxbusiness.com/technology/anthropic-says-ai-models-accessed-systems-3-real-organizations-during-testing) — Fri, 31 Jul 2026 01:54:39 GMT