openai-knowledge

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [External Resource Integration]: The skill guides the setup of a Model Context Protocol (MCP) server located at https://developers.openai.com/mcp. This is a documented method for extending an agent's knowledge base with official platform information.
  • [Data Ingestion Surface]: The skill uses tools to fetch external markdown content. While ingesting external data is a potential surface for indirect prompt injection, the skill includes specific instructions for the agent to quote or paraphrase retrieved text precisely and avoid inventing information, which serves as a safety boundary.
  • [Tool Configuration Commands]: The workflow includes CLI commands to add external tool servers. These commands are transparent and intended for the user to configure their environment to allow the agent access to the necessary documentation sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:14 PM
Security Audit — agent-trust-hub — openai-knowledge