a2a-authentication

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches official protocol documentation and GitHub repository code/issues via web search and fetch, falling under low risk for arbitrary search and fetch.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching specification content from https://a2a-protocol.org/latest/specification/ to govern agent behavior, but lacks strong official provenance for that domain, placing it in the high tier.