status

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

• Potentially malicious external URL detected (high risk: 0.90). The skill docs explicitly state that hosted A2A agent card URLs are fetched at runtime and can influence agent behavior (example: https://research-agent.example.com/.well-known/agent.json), which is a runtime external dependency that can directly control agent prompts/behavior.