skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides and instructs the agent to execute local Python scripts (init_skill.py, package_skill.py, and quick_validate.py) to manage the skill development lifecycle. These scripts are used for directory creation, file writing, and ZIP packaging. Analysis of the source code confirms they implement safety checks, including path normalization to prevent directory traversal and explicit rejection of symlinks during packaging to prevent arbitrary file inclusion.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:08 AM
Security Audit — agent-trust-hub — skill-creator