gws-drive

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill documents standard interactions with Google Drive using the 'gws' CLI and provides reference links to official documentation on developers.google.com.
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by retrieving and processing external content from Google Drive.
  • Ingestion points: Data is retrieved from external sources via API methods like 'files.get', 'files.list', 'comments.get', and 'replies.get' as documented in 'SKILL.md'.
  • Boundary markers: No explicit delimiters or instructions to ignore potential commands within the retrieved content are specified in the provided instructions.
  • Capability inventory: The skill possesses the ability to create, update, and delete files, as well as manage sharing permissions across the Google Drive environment.
  • Sanitization: The skill does not describe any validation or sanitization of the content fetched from the Drive API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 12:25 PM
Security Audit — agent-trust-hub — gws-drive