gmail

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses ClawLink to access Gmail and fetch message bodies/attachments at runtime (e.g., via gmail_fetch_emails / gmail_fetch_message_by_message_id), which ingests outsider-authored email free text into the agent’s LLM context.

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 downloads and executes the CLI package from https://www.npmjs.com/package/@useclawlink/cli at runtime, and that fetched code drives the Gmail actions (reads/writes) the agent performs, so it is a required remote executable dependency.