SafetyPage

Lab system cards and frameworks · System card · OpenAI

Addendum to GPT-5 System Card: GPT-5-Codex

15 Sep 2025

Read at openai.com ↗Read at sourceAll rights reserved

Outline · 7 pages

  1. Baseline Model Safety Evaluationsp. 2
  2. Disallowed Content Evaluationsp. 2
  3. Jailbreaksp. 2
  4. Model-Specific Risk Mitigationsp. 3
  5. Harmful Tasksp. 3
  6. Risk descriptionp. 3
  7. Mitigationp. 3
  8. Prompt Injectionp. 4
  9. Risk descriptionp. 4
  10. Mitigationp. 4
  11. Preparednessp. 5
  12. Biological and Chemicalp. 5
  13. Cybersecurityp. 5
  14. Product-Specific Risk Mitigationsp. 6
  15. Agent sandboxp. 6
  16. Network accessp. 6