gws-docs
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the 'gws' command-line interface to manage Google Docs resources. This is the intended and documented behavior for the skill.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves data from external documents. Mandatory Evidence Chain: 1. Ingestion points: 'gws docs documents get' (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: 'batchUpdate', 'create', 'get' (SKILL.md). 4. Sanitization: Not specified.
Audit Metadata