clerk-swift

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

• Third-party content exposure detected (low risk: 0.10). The workflow instructs the agent to visit and read an arbitrary markdown URL derived from the installed clerk-ios package README (WebFetch), which constitutes low-risk exposure to external 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 visiting remote quickstart documentation via URLs derived from package README files, but these instructions govern the agent's behavior and constitute an inbound operational dependency on an arbitrary third-party location.