document-scanning
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes standard system utilities (Bash find, PowerShell Get-ChildItem, and Git) to discover document files. It does not perform any network operations or access sensitive system credentials.
- [SAFE]: The scanning logic includes best-practice exclusions for sensitive or irrelevant directories such as .git, node_modules, .vscode, and pycache, reducing the risk of accidental sensitive data exposure.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a context passing format that interpolates file paths and user notes for sub-agents, which represents a potential injection surface.
- Ingestion points: System file paths discovered from the file system and user-provided notes.
- Boundary markers: The skill uses markdown headers and bold text keys to structure the delegated context blocks.
- Capability inventory: Shell command execution via Bash, PowerShell, and Git operations.
- Sanitization: No specific sanitization or escaping logic is defined for the discovered file paths or user notes before they are passed to sub-agents.
Audit Metadata