# OpenAI — Third-party cyber evaluations involving OpenAI models

- Company: OpenAI (openai.com)
- Announced: 2026-08-04T19:00:00+00:00
- Category: safety-policy-update
- Subject: GPT / ChatGPT / API
- Source: https://openai.com/index/third-party-cyber-evaluations-involving-openai-models
- Record: https://forck.live/items/3566-third-party-cyber-evaluations-involving-openai-models

OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.

## Evidence

Verbatim from https://openai.com/index/third-party-cyber-evaluations-involving-openai-models:

> OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.

## Follow-ups

- Simon Willison (reported, 5 Aug): Third-party cyber evaluations involving OpenAI models — https://forck.live/items/3578-third-party-cyber-evaluations-involving-openai-models

---

Record: https://forck.live/items/3566-third-party-cyber-evaluations-involving-openai-models
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md