recipe-find-large-files
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gws drive files listcommand to retrieve file metadata, including IDs, names, and sizes, from Google Drive to help users identify storage usage. - [INDIRECT_PROMPT_INJECTION]: The skill ingests file names and owner information from external Google Drive storage, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Results from the
gws drive files listcommand (SKILL.md). - Boundary markers: Absent.
- Capability inventory: Execution of the
gwsCLI tool. - Sanitization: No sanitization of the retrieved file metadata is performed before display or review.
Audit Metadata