google-meet
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly exposes endpoints (via https://gateway.maton.ai to Google Meet) to fetch user-generated conference data—e.g., GET /google-meet/v2/conferenceRecords/{conferenceRecordId}/transcripts and /entries and recordings—so the agent can ingest arbitrary third‑party (meeting) content that could contain instructions influencing subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata