ticktick

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow uses ClawLink to “open browser → authorize Ticktick” and then the agent runs actions/describe/run commands that fetch Ticktick task/action data (outsider-authored content from the user’s Ticktick account) and inject it into the agent’s LLM context as readable text.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run "npx @useclawlink/cli", which will fetch and execute remote code from the npm package (see https://www.npmjs.com/package/@useclawlink/cli) and then interact with the ClawLink service (https://claw-link.dev), so this is a runtime dependency that executes remote code and controls agent actions.