chatgpt-apps
Warn
Audited by Snyk on Apr 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill requires a runtime MCP docs tool at https://developers.openai.com/mcp (and fetches Apps SDK pages like https://developers.openai.com/apps-sdk/...) to retrieve current documentation that the agent must fetch and follow to drive its prompt/content generation, so the external URL is used at runtime and directly controls the agent's instructions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata