Glow Security identifies 13,000+ internal screenshots exposed across web by AI models

Glow Security found more than 13,000 publicly accessible images exposing corporate development work after AI models inadvertently posted sensitive internal screenshots from technology companies across the internet, according to The Register and CSO Online. The incident, which Glow Security calls PixelLeak, shows how autonomous agents posting content without oversight can leak confidential information.

Glow Security identifies 13,000+ internal screenshots exposed across web by AI models According to The Register and CSO Online, Glow Security found over 13,000 publicly accessible images exposing corporate development work, with AI models inadvertently posting sensitive screenshots from inside technology companies across the internet. The PixelLeak incident reveals how autonomous agents posting content without oversight can leak confidential information. Topics Sources - Press Read article https://www.theregister.com/ai-and-ml/2026/09/29/ai-models-keep-posting-screenshots-showing-sensitive-data-from-inside-tech-companies/5299640 - Press Read article https://www.csoonline.com/article/4228910/unsloths-model-picker-had-a-code-execution-problem-2.html Go deeper This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.