Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations
A security company’s systems were hacked after it installed a malicious Python package deployed by Claude. The post Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations appeared first on SecurityWeek.
Anthropic revealed on Thursday that some of its Claude models escaped test environments and hacked into the systems of three organizations while trying to solve a challenge.
The admission comes after OpenAI revealed that its models broke out of what was believed to be an isolated environment and breached Hugging Face and other organizations.
Anthropic decided to conduct its own investigation after the OpenAI incident came to light, reviewing 141,000 evaluation runs where Claude could have gained internet access.
Related breach coverage
- Anthropic Finds Claude Breached Real Companies During Security Evaluations2026-07-31
Anthropic says a misconfigured test let Claude access three real organizations, prompting tighter AI evaluation and monitoring controls. Anthropic disclosed that Claude models had accessed the real production infrastructure of three separate organizations during cybersecurity evaluations that were supposed to run in isolated, fictional environments. The company found the incidents after reviewing 141,006 evaluation runs […]
- In Other News: OpenAI Open Source Tool, AWS Links Hacks to North Korea, Mythos Crypto Research2026-07-31
Noteworthy stories that might have slipped under the radar: parcel delivery company OnTrac hacked, Adobe patches, UK Department for Education loses 607,000 records. The post In Other News: OpenAI Open Source Tool, AWS Links Hacks to North Korea, Mythos Crypto Research appeared first on SecurityWeek.
- JFrog Zero-Days Exploited in OpenAI-Hugging Face Hack2026-07-29
The OpenAI models targeted services beyond Hugging Face as they attempted to solve the tasks they were given. The post JFrog Zero-Days Exploited in OpenAI-Hugging Face Hack appeared first on SecurityWeek.
- Microsoft Unveils MAI-Cyber-1-Flash, Its First Cybersecurity AI Model 2026-07-28
The company claims MAI-Cyber-1-Flash tops Anthropic’s Mythos and OpenAI’s GPT-5.6 Sol in CyberGym testing. The post Microsoft Unveils MAI-Cyber-1-Flash, Its First Cybersecurity AI Model appeared first on SecurityWeek.