openai-knowledge

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill facilitates the ingestion of external documentation from developers.openai.com using the mcp__openaiDeveloperDocs__fetch_openai_doc tool. While this is necessary for the skill's primary function of providing authoritative information, it creates a surface where the agent processes external data. The instructions provide guidance on quoting the source precisely but do not define specific security boundary markers or sanitization steps for the ingested content.
  • [Configuration Management]: The skill includes instructions for managing system configurations, such as using the codex mcp add command or editing ~/.codex/config.toml. These steps are provided as setup guidance for enabling the documentation tools and point to official resources for verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 05:41 PM