google-meet

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 interact with Google Meet and fetch meeting/transcript content at runtime (e.g., googlemeet_get_transcripts_by_conference_record_id / googlemeet_get_transcript_entry), which is outsider-authored free text from other meeting participants.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx @useclawlink/cli" which fetches and executes remote npm package code at runtime (see https://www.npmjs.com/package/@useclawlink/cli), so an external package is required and runs code that can control the agent.