filesystem

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of documentation and boilerplate hooks for managing local files using native agent capabilities and contains no malicious logic.
  • [COMMAND_EXECUTION]: The instructions demonstrate using the Bash tool for common directory tasks like listing (ls), creating (mkdir), and moving (mv) files.
  • [PROMPT_INJECTION]: The skill establishes an inherent surface for indirect prompt injection by processing file contents from the local filesystem.
  • Ingestion points: File reading and content searching via the Read, Grep, and Glob tools (SKILL.md).
  • Boundary markers: Not present; instructions do not provide delimiters for untrusted file content.
  • Capability inventory: Includes modification tools (Write, Edit) and command execution (Bash).
  • Sanitization: Not present for ingested file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 12:14 AM