a2a-client

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches documentation from a URL and search engine, which is low-risk user-selected or public content fetching.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching live protocol documentation from a2a-protocol.org, which constitutes an external operational dependency with unverified provenance, resulting in a high tier.