gws-drive
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data (file content, metadata, comments) from the Google Drive API which represents an attack surface for indirect prompt injection.
- Ingestion points: API responses from methods like
files.get,files.list, andcomments.listas documented inSKILL.mdbring external, untrusted content into the agent context. - Boundary markers: The skill documentation does not specify explicit boundary markers (e.g., XML tags or delimiters) to separate retrieved content from agent instructions.
- Capability inventory: The skill has high-impact capabilities including file deletion (
files.delete), permission management (permissions.create), and content exfiltration/download (files.download). - Sanitization: There is no evidence of content sanitization or instruction-filtering for the data retrieved from Google Drive before it is processed by the agent.
Audit Metadata