a2a-multi-turn

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 https://a2a-protocol.org/latest/specification/ and conducts web searches for GitHub repositories, which is low-risk active retrieval of external pages.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs fetching the live specification from an unofficial domain a2a-protocol.org, which constitutes an unverifiable runtime external dependency under common/reputable unofficial provenance.