ap2-agent-authorization

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 ap2-protocol.org and performs web searches for reference code on GitHub, which is low-risk user- or public-facing content fetch.

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 instructions and specification content from ap2-protocol.org at runtime to govern its behavior, which constitutes an operational dependency with unverified first-party provenance.