google-agents-cli-publish

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's A2A registration flow explicitly fetches and consumes an agent card from an arbitrary --agent-card-url (see "A2A Registration" and the example agent-card.json URL), meaning it reads untrusted third-party content that can influence registration behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches an external agent card at runtime (https://my-service-abc123.us-east1.run.app/a2a/app/.well-known/agent-card.json) to perform A2A registration, meaning remotely served content can directly control the agent's registration/configuration and thus its runtime behavior.