recipe-bulk-download-folder

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source (Google Drive) which could contain malicious instructions designed to influence the agent's behavior during the automation process.
  • Ingestion points: The output of gws drive files list (which includes file names, IDs, and metadata) enters the agent's context as specified in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific "ignore" warnings to prevent the agent from following instructions potentially embedded in file names or metadata.
  • Capability inventory: The skill utilizes gws drive files get and gws drive files export, which involve writing files to the local file system and performing network operations via Google Workspace APIs.
  • Sanitization: No sanitization or validation steps are defined for the file metadata retrieved from the listing command before it is interpolated into subsequent download and export commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:17 PM
Security Audit — agent-trust-hub — recipe-bulk-download-folder