google-calendar

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 read Google Calendar data at runtime (e.g., listing/getting events), and those event titles/descriptions/comments are outsider-authored free text from other people on the user’s calendar that the agent ingests into its LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running "npx @useclawlink/cli" at runtime, which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and interacts with ClawLink (https://claw-link.dev), so external content is executed and required for the skill to function.