recipe-review-meet-participants
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes conference attendee information and session logs retrieved from Google Meet, which constitutes untrusted external data.
- Ingestion points: Meet conference records and participant lists accessed via the
gwstool inSKILL.md. - Boundary markers: The instructions do not define specific delimiters for the external data or include warnings to ignore instructions embedded in participant metadata.
- Capability inventory: The skill is limited to listing and displaying records using the
gwscommand-line tool. - Sanitization: There is no evidence of sanitization or filtering applied to the data retrieved from the Google Workspace API.
Audit Metadata