chatgpt-apps
Warn
Audited by Snyk on Jun 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires fetching current Apps SDK docs at runtime (via the OpenAI docs MCP endpoint https://developers.openai.com/mcp and canonical docs URLs such as https://developers.openai.com/apps-sdk/build/mcp-server/) and uses that fetched content to drive scaffolding prompts and generated code, so this is a runtime external dependency that directly controls agent instructions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata