ap2-cryptographic-signing

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches external web pages and runs web searches (low risk active search), but does not monitor or consume outsider-submitted free text or feeds automatically (no medium risk sources).

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs fetching specification and documentation URLs (https://ap2-protocol.org/...) to guide its implementation behavior, which constitutes an inbound operational dependency on external content.