recipe-review-meet-participants
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues or malicious patterns were identified in the provided skill file.
- [COMMAND_EXECUTION]: The skill uses the 'gws' command-line tool to interact with Google Meet APIs. These commands are restricted to listing and retrieving conference metadata and participant lists, which aligns with the skill's stated purpose of reviewing attendance.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Google Meet conference and participant records, which serves as a potential surface for indirect instructions.
- Ingestion points: Conference records, participant names, and session IDs retrieved via the
gws meetcommand (SKILL.md). - Boundary markers: None present in the instructions.
- Capability inventory: Data retrieval and table-formatted display via the
gwsbinary. - Sanitization: None present in the provided instructions.
Audit Metadata