recipe-batch-rename-files
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from Google Drive file names, which can be used to influence agent behavior.\n
- Ingestion points: The
gws drive files listcommand retrieves external file metadata into the agent context (SKILL.md).\n - Boundary markers: No delimiters or safety instructions are provided to separate retrieved data from agent logic.\n
- Capability inventory: The skill possesses file modification capabilities via the
gws drive files updatecommand (SKILL.md).\n - Sanitization: There is no mention of sanitizing or validating the content of the file names before processing.
Audit Metadata