NYC

Command Development

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): The skill consists entirely of Markdown documentation and reference materials.
  • [COMMAND_EXECUTION] (SAFE): While the skill documents how to use the Bash execution feature (!\command`), it does so for educational purposes and correctly emphasizes using restrictive tool filters (e.g., Bash(git:*)`) as a security best practice.
  • [DATA_EXPOSURE] (SAFE): Examples include commands that read file content (@path) or git status. These are standard platform features described in an educational context to help developers manage their own projects.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill explains how to use dynamic arguments ($1, $ARGUMENTS) and file references. While these ingest untrusted data, the documentation provides guidance on using disable-model-invocation for sensitive or manual-only operations, which is a key mitigation for this attack vector.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:04 PM