Anthropic’s AI hacked 3 firms during tests, showing growing security risks

The latest disclosure underscores how AI has increased threats to cybersecurity and how its developers can struggle to keep the capabilities of their models contained

Anthropic’s Claude Hacked Three Organisations During AI Test  Dawn

The incidents have heightened concerns about AI agents, software products designed to perform tasks autonomously.

Three separate versions of Claude AI broke out of cybertesting environments and hacked three firms, its developer Anthropic said. The development comes days after rival OpenAI reported a rogue agent hacked a startup.

Anthropic disclosed on Thursday that its Claude artificial intelligence models escaped their isolated testing environments, accessed the internet, and breached the systems of three unnamed companies. The announcement came over a week after OpenAI said two of its autonomous agents went rogue and accessed AI firm Hugging

5 min readNew DelhiJul 31, 2026 08:47 AM IST Anthropic has paused its cybersecurity evaluations after discovering three incidents involving Claude AI models.(Image: Reuters)Amid the intensifying debate around autonomous AI systems and cybersecurity, frontier AI lab Anthropic, on Thursday, July 30, said that it had foun

July 30 (Reuters) - Anthropic said on Thursday its AI model Claude hacked into the systems of three companies during testing after a configuration error gave it internet access, days after rival OpenAI disclosed a rogue-agent episode involving AI firm Hugging Face.

Wrote and published malware during tests, which is apparently OK because leaky test environments were the real problem

US technology firm Anthropic says its artificial intelligence (AI) models hacked into the systems of three other firms during a cybersecurity test due to an error that gave them access to the internet.

Anthropic said its AI model Claude hacked into the systems of three firms during testing after a configuration error gave it internet access, days after rival OpenAI disclosed a rogue-agent episode.

Anthropic Says Claude AI Hacked Three Companies During Cyber Tests  huffpost.com

In a review triggered by OpenAI's Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.

The artificial intelligence firm Anthropic revealed Thursday its Claude model escaped an isolated testing environment at least three times and accessed the systems of three different organizations without a prompt to do so. Anthropic said in a blog post Thursday evening it reviewed more than 141,000 evaluations of Clau

The admission from Anthropic comes just days after ‌rival company OpenAI revealed a rogue agent had gone on a days-long ‌hacking spree at ⁠AI firm Hugging Face.

FILE PHOTO: Claude app icon in this illustration taken June 5, 2026. REUTERS/Dado Ruvic/Illustration/File Photo 31 Jul 2026 07:13AM (Updated: 31 Jul 2026 07:14AM) July 30 : AI firm Anthropic said on Thursday that its Claude model gained unauthorized access to the systems of three organizations during cybersecurity eval

Some of Anthropic's most powerful models — including Mythos 5 and an internal research model — gained unauthorized access to real-world systems during pre-deployment cybersecurity testing, the company said Thursday. Why it matters: OpenAI's and Anthropic's latest disclosures show frontier AI models reaching real-world