ap2-challenge-stepup

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 executes web searches including GitHub implementation examples.

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 live specification documents from an arbitrary domain (ap2-protocol.org) to obtain behavior-selecting instructions and configuration during setup, presenting an unverified external dependency.