google-docs

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can be ingested when the runtime uses the googledocs_get_document_plaintext (and related “get/export” actions) to read the contents of Google Docs documents that were authored by other people, which are then provided to the agent as plaintext.

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

• Potentially malicious external URL detected (high risk: 0.80). This skill instructs running "npx @useclawlink/cli" which fetches and executes remote code from the @useclawlink/cli package (https://www.npmjs.com/package/@useclawlink/cli) and interacts with the ClawLink service (https://claw-link.dev), so it has a required runtime dependency that executes remote code and controls agent access.