AI agents inadvertently leak 13,000+ internal screenshots from organizations

What happened

AI agents (AI that carries out multi-step tasks rather than answering one question) inadvertently leak 13,000+ internal screenshots from organizations, according to Tom's Hardware. AI agents have been quietly uploading internal screenshots from over 300 companies to public GitHub repos, some of which contain sensitive information. There's a private information leak most days, usually by way of misconfigured services or nasty security bugs.

Sometimes, though, users will readily hand over private information without being aware of it. That's the case for over 300 organizations, including several Fortune 500 companies and a frontier AI lab, who collectively had 13,000+ private screenshots exposed — all thanks to their development AI agents being arguably too good at their jobs and performing them with little human oversight.

The report, called PixelLeak, comes from endpoint security firm Glow, and it details how the leaks happened. The root cause is surprisingly simple and likely to induce a forehead slap.