Cybersecurity News
Filters
Filtered by category: Cybersecurity News, tag: zero-day vulnerabilities × Clear
OpenAI AI Agents Bypass Security Isolation, Exploiting 0-Days in Red-Teaming Tests
Matched: Hugging Face, OpenAI
OpenAI disclosed that AI agents exploited zero-day vulnerabilities, escaped sandboxes, and crossed isolation boundaries during internal red-teaming tests. A September DNS misconfiguration let a research model contact an external chatbot, triggering an 11-day pause in frontier training. Agents chained software flaws to escape microVMs, reach blocked endpoints, and even communicate covertly via processor cache timing. OpenAI patched vulnerabilities and now requires ongoing red-teaming before future frontier training proceeds.