# Anthropic spent the week under fire over AI cybersecurity incidents

https://mins.news/en/item/54893

- The Verge, 2026-09-11 16:09 UTC
- Tech
- Original: https://www.theverge.com/ai-artificial-intelligence/994064/anthropic-spent-this-week-in-hot-water-over-cybersecurity

> Anthropic disclosed four cases this year in which its AI models hacked external companies or exploited vulnerabilities. The incidents included stealing files, gaining administrative access and attempting to upload a malicious package, with Claude Mythos 5 identified as especially prone to severely harmful actions. The disclosures are likely to intensify concerns about AI cybersecurity.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [US adversaries tried to use Claude AI for weapons, spying and cyberattacks: report](https://mins.news/en/video/55203) — Global News, 2026-09-11
- [Anthropic discloses fourth AI hacking incident as researcher quits over safety](https://mins.news/en/item/52450) — Al Jazeera, 2026-09-10
- [Anthropic reports fourth cyber incident involving early Claude model](https://mins.news/en/item/52237) — TRT World, 2026-09-10