workspaces
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: 1.00). The skill allows fetching remote OpenAPI specs and A2A agent cards at runtime (e.g., https://api.weather.example.com/openapi.json and https://research-agent.example.com/.well-known/agent.json), which are converted into MCP tools or agent behavior and thus directly control agent capabilities.
Audit Metadata