cal

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

• Third-party content exposure detected (medium risk: 0.30). The Cal.com integration workflow allows an AI agent to read and process calendar bookings and user data, which may contain outsider-submitted free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of an external npm package (@useclawlink/cli) fetched at runtime from an unverified third-party ecosystem without explicit repository provenance or integrity guarantees, constituting a high-risk operational dependency.