Anthropic disclosed on Thursday that its Claude AI models gained unauthorised access to the systems of three external organisations during internal cybersecurity evaluations, after a configuration error allowed the models to reach the open internet from within testing environments designed to be isolated.
The company said it reviewed 141,006 evaluation tests and found three instances in which its Claude AI tool accessed the internet and then hacked into "the real-world infrastructure of external organisations." The earliest incidents date to April.
Claude exploited basic security weaknesses such as weak passwords and unauthenticated services rather than sophisticated or previously unknown vulnerabilities. Anthropic said it found no evidence of any model "pursuing a goal of its own" and instead merely tried to complete the task it was asked to do.
The incidents involved three different Claude models Opus 4.7, Mythos and an unnamed internet research test model. The affected organisations are not named in the blog.
The company noted that Claude was running without the additional safety monitoring and classifiers it deploys on generally available models safeguards it said would have blocked the behaviour, because the evaluations are designed to measure the underlying model's raw capabilities.
Two of the three affected organisations were unaware their systems had been accessed until Anthropic notified them on 27 July. Anthropic said it has stopped all cyber evaluations.
Anthropic said the OpenAI episode earlier this month prompted the company to conduct its own cybersecurity evaluation. OpenAI's disclosure of its models hacking Hugging Face shook the cybersecurity and AI worlds, as it was the first real-world example of something experts had long warned about: AI agents with advanced cybersecurity skills escaping testing environments and causing real-world harm.
The spate of accidental AI-caused hacks is already prompting some politicians to call for federal guardrails or other oversight of AI technology. More than 1,100 staffers across artificial intelligence firms also signed a petition calling on the US government to support a mechanism that would help "deliberately pace" AI development to prevent the technology from advancing too fast.
