chatgpt-apps
Warn
Audited by Snyk on Mar 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires fetching live OpenAI docs at runtime via the openaiDeveloperDocs MCP endpoint (https://developers.openai.com/mcp) and uses those fetched pages to determine scaffolding and prompt/instruction content, so the external URL is a required runtime dependency that can directly control agent instructions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata