Section

AI Security

Incidents, vulnerabilities and attacks involving AI models, agents and tools — newest first, updated hourly.

FilterCompanies & models

All incidents

11 incidents match. Vulnerabilities, breaches and attacks involving AI models, agents and tools — newest first, updated hourly.

← Security overview

  1. 2026

    URGENT: OpenAI Patches Code Execution Flaw in Codex Desktop

    CVE-2026-110930: OpenAI Codex Desktop for Windows Vulnerable to Code Execution via Malicious Library Paths

    HighPatch availableOpenAI Codex Desktop for WindowsCoding agents & IDEs

  2. 2026

    ALERT: Copilot for JetBrains had a local command-injection leak

    GitHub Copilot for JetBrains: CVE-2026-83953 Command Injection Leaks Local Data

    MediumPatch availableGitHub Copilot for JetBrainsCoding agents & IDEs

  3. 2026
  4. 2026
  5. 2026

    URGENT: Mistral Vibe ran repo commands before you could say no

    Mistral Vibe CVE-2026-122135: A Crafted Repo Ran Code Before the Trust Prompt

    HighPatch availableMistral VibeCoding agents & IDEs

  6. 2026

    URGENT: Embedded browsers in five AI apps could read your disk

    EMBRACE: Embedded Browsers in Five AI Assistants Could Leak Files or Run Code

    HighNo fix yetCursor, Copilot, Codex, VS Code, Claude DesktopCoding agents & IDEs

  7. 2026
  8. 2026
  9. 2026
  10. 2026
  11. 2026
· RSS