skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOW
Full Analysis
  • [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found. Documentation files provide benign structural guidance for output and workflows.
  • [Data Exposure & Exfiltration] (SAFE): The scripts perform local file operations for packaging purposes and do not access sensitive system paths (~/.ssh, ~/.aws) or perform network requests.
  • [Unverifiable Dependencies] (LOW): The project depends on the PyYAML library for parsing skill metadata. While an external dependency, it is a standard library for this purpose.
  • [Indirect Prompt Injection] (SAFE): quick_validate.py uses yaml.safe_load() to process skill frontmatter, which is the secure method for preventing code execution through malicious YAML payloads.
  • [Dynamic Execution] (SAFE): No instances of eval(), exec(), or unsafe subprocess calls using untrusted input were detected. File zipping and validation logic are implemented using standard, safe Python APIs.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 05:16 AM