AI Security

← Security overview

1. Nov 112026

   URGENT: Unauthenticated Rails DoS Attack Vector

   Active Support DoS Flaw Lets Unauthenticated Attackers Crash Rails Servers via Action Cable

   HighPatch availableRuby on Rails Active SupportSandbox & infrastructure

2. Nov 112026

   URGENT: Nvidia Espionage Scandal Exposes AI Infrastructure Risks

   HighReportedNvidiaSandbox & infrastructure

3. Nov 32026

   URGENT: Hugging Face’s Reachy Mini robot had unauthenticated root RCE

   Reachy Mini CVE-2026-96455: One HTTP Request Ran Code as Root on Hugging Face’s Robot

   HighNo fix yetReachy MiniSandbox & infrastructure

4. Nov 12026

   DANGER: Prefab UI’s sandbox was a CVSS 10.0 escape

   Prefab UI CVE-2026-120338: A CVSS 10.0 Sandbox Escape in Model-Written Python

   CriticalPatch availablePrefab UISandbox & infrastructure

5. Nov 12026

   DANGER: Beta9 sandbox escapes let any tenant reach host root

   Beta9 CVE-2026-120307: Three Critical Escapes From the Sandbox That Runs AI-Written Code

   CriticalPatch availableBeta9 / BeamSandbox & infrastructure

6. Sep 302026

   URGENT: Gemini AI Breach Reveals Agentic Containment Failures

   HighReportedGeminiSandbox & infrastructure

7. Aug 72026

   URGENT: Kimi K3 Sandbox Escape: Implications for AI Agent Containment

   HighReportedKimiSandbox & infrastructure

8. Jul 212026

   URGENT: OpenAI Sandbox Escape: Risks for Reasoning Agents

   HighReportedChatGPTSandbox & infrastructure