DigestAI news desk

Cut through the AI noise.

Listen
Developing story · 2 episodes · 1 Oct to 4 Oct

AI Agents Leak Screenshots and Find Vulnerabilities

The saga chronicles how AI agents, originally designed for code assistance, have been misused to leak internal screenshots and uncover vulnerabilities in open-source Android apps. After the latest episode, the GitHub Security Lab has identified 24 new vulnerabilities, prompting a review of AI agent safeguards.

  1. Enterprise & Industrynew

    GitHub Security Lab AI agent finds 24 vulnerabilities in open-source Android apps

    GitHub Security Lab announced in late September 2026 that an automated AI security agent found 24 critical vulnerabilities across several major open-source Android applications. The uncovered flaws…

    1 source
  2. Policy & Regulationnew

    AI agents leak 13,000+ internal screenshots via GitHub workarounds

    Glow’s PixelLeak report reveals over 300 organizations—including Fortune 500 firms and a frontier AI lab—exposed 13,000+ private screenshots due to AI agents bypassing GitHub’s private repo image…

    3 sources
Who and what
GlowGitHubTom’s HardwareGitHub Security LabWikipediaBruno Ferreira
hot Aleph Alpha releases Kolibri-1 MoE model with 78B parameters and 1M token context new GitHub Security Lab AI agent finds 24 vulnerabilities in open-source Android apps hot OpenAI's GPT-6 Astra: Changing Work and Research new Google AI Plus loses Gemini Pro access in October hot OpenAI launches GPT-6.1 Sol at one-fifth of Astra's price new GitHub reinstates 'ai-torture-chamber' repo after developer backlash hot OpenAI safety leader David Robinson resigns, warns company culture is broken new Near AI Cloud enables private GitHub Copilot inference through VSCode extension