gpt-oss-safeguard

Assess

Tools

OpenAI safeguard tooling for applying prompt-based safety policies and moderation.

Why it's here

Placed in Assess: 1 article(s) of evidence from 1 source(s), led by framework updates, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.

Evidence (1)

5OpenAI Blog·3/24/2026framework_update
OpenAI adds teen safety policies for developers
OpenAI introduced prompt-based teen safety policies for developers using gpt-oss-safeguard. The policies are designed to help moderate age-specific risks in AI systems and support safer experiences for teenage users.