cal

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

• Third-party content exposure detected (medium risk: 0.65). Cal.com actions are executed via ClawLink, which at runtime uses the user’s browser/OAuth session to call Cal.com and ingest Cal.com’s responses (including free-form text like event/booking details) into the agent’s LLM context; this content is authored by an external third-party service (Cal.com) rather than the operating user.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill requires running "npx @useclawlink/cli" which causes runtime fetching and execution of remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli), and that fetched CLI directly performs and controls the agent's Cal.com actions.