gws-classroom
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the 'gws' binary to execute administrative commands for Google Classroom. This is consistent with its stated purpose and vendor origin.
- [PROMPT_INJECTION]: The skill processes data from Google Classroom which represents an indirect prompt injection surface. Ingestion points: courses, announcements, and posts. Boundary markers: None. Capability inventory: gws classroom API commands. Sanitization: Relies on the underlying GWS API and CLI sanitization. The risk is assessed as safe given the trusted vendor context.
Audit Metadata