jobs
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: 0.90). The skill explicitly fetches remote agent/MCP OpenAPI specs at runtime (e.g., the OpenAPI example URL "https://api.weather.example.com/openapi.json" and the hosted agent card URL "https://research-agent.example.com/.well-known/agent.json"), and those fetched specs are converted into MCP tools/agent behavior that directly control prompts and agent capabilities.
Audit Metadata