openai-docs-skill

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill performs runtime requests to the MCP endpoint (https://developers.openai.com/mcp) and uses the fetched documentation (via search_openai_docs / fetch_openai_doc) as authoritative content to drive agent responses, so remote content can directly control prompts and is a required dependency.