a2a-messages-parts

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

• Third-party content exposure detected (low risk: 0.10). The workflow requires fetching live documentation URLs and web-searching GitHub for schema details and code examples.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch external specifications from an unverified domain at runtime, resulting in a high-risk unverifiable operational dependency.