gws-docs-write
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the 'gws' CLI binary to perform document append operations.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes user-provided text that is written to a document, which could be later processed by an agent. 1. Ingestion points: The '--text' parameter defined in SKILL.md. 2. Boundary markers: None present to delimit the inserted text from existing document content. 3. Capability inventory: The skill uses the 'gws' binary to write to external Google Docs. 4. Sanitization: No text sanitization or filtering is specified within the skill definition.
Audit Metadata