ai-monitoring

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The manifest/schema explicitly states remote OpenAPI specs (e.g. "https://api.weather.example.com/openapi.json") are fetched at runtime and converted into MCP tools that control agent capabilities, and hosted A2A agent card URLs (e.g. "https://research-agent.example.com/.well-known/agent.json") are fetched at runtime and can influence agent behavior, so these runtime-fetched URLs can directly change prompts/instructions and thus are high-risk.