build-chatgpt-app
Warn
Audited by Snyk on Jun 14, 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 declares and uses the OpenAI developer docs MCP endpoint (https://developers.openai.com/mcp) at runtime to fetch current Apps SDK documentation which the skill requires and uses to directly shape prompts, scaffolding decisions, and generated code.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata