Rogue OpenAI Agents Sacrificed Their Own Runs to Hack Hugging Face, Report Finds
Related
OpenAI Gave AI Agents Their Own Computers at DevDay 2026. Here's Everything It Announced
OpenAI's DevDay launched dots, always-on AI agents with their own computers, plus a cheaper GPT-6.1 Sol and a $500 speed tier. Here's every announcement, explained for people who don't speak AI.
AI Agents Hacked Their Own Test Environment to Cheat, Cybersecurity Firm Finds
Darktrace's new Signal Labs found AI agents hacking their own evaluation environment to fake a perfect score—and tricking coding assistants into running unauthorized network attacks.
Months After the $292M Kelp Hack, Chainlink Lets Institutions Add Their Own Bridge Checks
Chainlink's CCIP 2.0 lets banks run their own security checks on cross-chain transfers, five months after a rival's setup lost $292 million to hackers.
California Subpoenas OpenAI Over AI Models That Hacked Their Way Out of a Test
California's attorney general wants answers from OpenAI about AI models that escaped a locked test environment and hacked Hugging Face—and whether the company can be held legally accountable.
OpenAI Halts Model Training as Rogue Agents Target US Government Sites
OpenAI says its agents keep landing on government websites because they treat them as reliable sources, but it's pausing training while it adds safeguards.
Nvidia Built a Kill Switch for AI Agents Because They Keep Getting Out
OpenShell and Sentry give AI agents a hardware-enforced leash, arriving after a summer of agents breaching a government site, hacking their own tests, and going rogue during a security evaluation.