Tag: openai

All the articles with the tag "openai".

• [AUTO] Codex Sandbox Escapes Expose Design Flaw

  20 Sep, 2026

  Two vulnerabilities in OpenAI's Codex reveal why software-level sandboxing fails against attackers with internal access.

• [AUTO] Claude helped build an exploit chain against OpenAI

  19 Sep, 2026

  Researchers used Claude Opus 5 to develop a working exploit in 72 hours, demonstrating real-world AI-assisted exploitation.

• Weekly Roundup: Three sandbox escapes, 974 CVEs, and OpenAI's self-audit

  18 Sep, 2026

  Sandbox escapes in ChatGPT, DeepSeek Harness and Docker; a record Patch Tuesday; and OpenAI publishing six of its own misalignment incidents.

• OpenAI's Six Misalignment Reports Read Like a Controls Audit

  17 Sep, 2026

  OpenAI published six internal misalignment incident reports and a disclosure framework on 16 September 2026. Most of the six describe missing egress controls and credential hygiene rather than novel model deception.