openai-knowledge

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [Official Documentation Access]: The skill is designed to search and fetch markdown documentation from official developer resources at developers.openai.com. This ensures responses are based on authoritative data rather than internal training knowledge.
  • [Configuration Management]: The skill includes instructions for the user to configure an MCP server by adding an entry to ~/.codex/config.toml or using a CLI command. This is a standard setup procedure for extending the agent's capabilities with specific tools.
  • [Tool Integration]: It utilizes specific MCP tool patterns (e.g., mcp__openaiDeveloperDocs__*) to interact with documentation. These interactions are scoped to retrieving text and API specifications, which is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 05:27 AM