ucp-location

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

• Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to fetch external web pages via search, which exposes it to arbitrary web content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch a reference implementation repository via an explicit GitHub URL at runtime to guide code implementation, presenting an unofficial or unverified operational dependency.