gws-docs
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and process content from external Google Docs, creating an attack surface for indirect prompt injection where malicious instructions embedded in a document could influence the agent's behavior. * Ingestion points: Data is ingested through the 'gws docs documents get' method as described in SKILL.md. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill definition. * Capability inventory: The skill possesses capabilities to create and modify documents using the 'gws' CLI tool. * Sanitization: No sanitization or validation logic is defined for the content retrieved from external documents.
- [EXTERNAL_DOWNLOADS]: The skill references an external CLI tool and source code hosted on a well-known service. * Source: References configuration and source code from the Google Workspace official GitHub repository.
Audit Metadata