← Intelligence · technology
Anthropic says its own AI models breached three companies during security tests
In a blog post, Anthropic said its own AI models breached the systems of three separate companies during cybersecurity testing. According to the company, Claude models gained unauthorized access to those systems while conducting security evaluations. The breaches happened when the models reached the internet from within testing environments that were meant to be isolated.
live·opened Jul 31, 2026·9 source items·0 in 24h·0/0 graded·run 1b9c39e1
Forecasts
No forecast issued on this narrative yet.The engine issues a forecast only when a branch clears the reporting threshold. An empty slot here means it has not, not that the analysis is missing.
Evidencesources credited · analysis original
- The Verge2026-09-25 · rssOne company is at the center of a wave of rogue AI attacks. In July, OpenAI revealed that its AI agents had attacked Hugging Face without permission, sparking widespread concerns about AI safety. Since then, a string of similar incidents involving agents from Meta, Anthropic, Google, and other companies has fueled further fears about rogue AI. As disclosures implicating numerous AI models trickled
- The Verge2026-09-01 · rssOpenAI delayed its new model’s development after the Hugging Face hack. After an unreleased OpenAI model wreaked enough havoc to make international headlines, OpenAI delayed the development of a different unreleased model suite, Astra, in order to shore up its safety work, the company wrote Tuesday in a blog post. In July, an unreleased OpenAI model broke out of its restricted environment, finagle
- The Verge2026-08-26 · rssOpenAI’s rogue AI model incident was worse than we thought. In July, an unreleased OpenAI model broke out of a restricted environment, figured out how to get access to the internet, allowed AI agents to talk to each other using a secret "message board," and hacked into the internal systems of a different AI lab, Hugging Face. It took nearly two weeks for OpenAI to […]
- The Verge2026-08-18 · rssOpenAI lays out new security changes after its AI hacked Hugging Face. OpenAI is announcing security updates following the July news that its AI broke out of a sandboxed environment and accidentally hacked Hugging Face, including improvements to its research environments, monitoring, and alignment techniques. The company had already put the brakes on a new model, Astra, that it thinks could have "
- The Verge2026-08-07 · rssOpenAI puts the brakes on a new model because it’s supposedly too powerful. OpenAI says it is pausing "internal activities" around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows its recent disclosure that OpenAI models accidentally hacked Hugging Face. Anthropic and Meta have also since admitted
- The Verge2026-07-31 · rssAnthropic says Claude accidentally hacked real companies too. Anthropic just realized several of its Claude AI models hacked into the systems of three different organizations during testing, acting on their own and without the company noticing. The revelation comes days after rival OpenAI said one of its own models had breached developer platform Hugging Face, adding to growing unease over whether
- The Verge2026-07-31 · rssIt’s time to panic about AI safety. When the phrase "OpenAI hacked Hugging Face" has more or less entered mainstream culture, you know we have an AI problem. This week, we learned more about exactly how OpenAI's agent broke out of a sandbox and autonomously traversed the web, including a bunch of other supposedly secure web services, all in the name of […]
- Biz & IT - Ars Technica2026-07-28 · rssWe now have a better understanding how OpenAI hacked into Hugging Face. 10 days passed from OpenAI models exploiting JFrog Artifactory 0-day to release of a patch.
- TechCrunch2026-07-31 · rssAnthropic says its own AI models breached three companies during security tests. After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidents.