google-meet

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly uses Membrane actions to fetch Google Meet content (e.g., "list-transcripts", "get-transcript", "list-transcript-entries" and recording/participant actions listed in SKILL.md), which are user-generated/untrusted meeting transcripts and recordings that the agent would read and could materially influence subsequent actions.