gws-meet
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and process external data from Google Meet conferences, creating a potential attack surface for indirect prompt injection.\n
- Ingestion points: The skill uses the
gws meet conferenceRecordsresource to retrieve conference records, participant information, recordings, and meeting transcripts (SKILL.md).\n - Boundary markers: The instructions lack specific boundary markers or instructions for the agent to treat data from transcripts or recordings as untrusted content.\n
- Capability inventory: The skill possesses capabilities to create, patch, and end meeting spaces using the
gws meet spacesresource (SKILL.md).\n - Sanitization: No sanitization or filtering logic is described for the content retrieved from transcripts or recordings before it is processed by the agent.
Audit Metadata