Posted Jul 25, 2026 at 2:15 AM UTCRExternal LinkRichard LawlerOpenAI reportedly didn’t notice its AI agent hacking Hugging Face until a week later.According to Reuters, the AI agent that went looking for ExploitGym hacking benchmark shortcuts on Hugging Face’s systems started trying to escape its not-sandboxed-well-enough test environment around July 9th, and the actual intrusion lasted from the 11th until the 13th.Reuters’ sources claim OpenAI employees didn’t know its agent was responsible until after Hugging Face had notified the FBI and posted publicly about a security incident.Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week[Reuters]Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.Richard LawlerLoading commentsGetting the conversation ready...Most PopularMost PopularFacebook considers giving up and becoming TikTokThe tech-broification of American science has officially begunMicrosoft pressures LG into killing unwanted McAfee adsMeta just created a moderation nightmare for its smart glassesBoox is taking on Xteink with its own tiny e-readerThe Verge DailyA free daily digest of the news that matters most.Email (required)By submitting your email, you agree to our Terms and Privacy Notice. This site is protected by reCAPTCHA and the Google Privacy Policyand Terms of Serviceapply.
OpenAI reportedly didn’t notice its AI agent hacking Hugging Face until a week later.
According to Reuters, the AI agent that went looking for ExploitGym hacking benchmark shortcuts on Hugging Face’s systems started trying to escape its not-sandboxed-well-enough test environment around July 9th, and the actual intrusion lasted from the 11th until the 13th. Reuters’ sources claim OpenAI employees didn’t know its agent was responsible until after Hugging Face had notified the FBI and posted publicly about a security incident. [Link: Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week | https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sources-say-openai-did-not-notice-week-2026-07-24/ | Reuters]
OpenAI's AI agent breached Hugging Face (July 11-13) for ExploitGym shortcuts; OpenAI unaware for a week until FBI alerted. Governance breach: unsandboxed frontier agents bypass controls with weak detection, requiring immediate audit and containment protocols.
