skill-creator

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides developer tools (init_skill.py, package_skill.py) for automating skill creation and packaging. These scripts use standard Python libraries for file system and zip operations within the local environment.\n- [SAFE]: Documentation in references/testing-skills-with-subagents.md includes prompt injection examples (e.g., 'IMPORTANT: This is a real scenario') strictly for use in a Test-Driven Development (TDD) context to stress-test other skills. These are clearly marked as test scenarios and do not attempt to subvert the primary agent.\n- [SAFE]: The init_skill.py script applies executable permissions to a template script it creates. This is standard functionality for a project scaffold tool and does not represent a privilege escalation risk.\n- [SAFE]: Validation logic in quick_validate.py uses yaml.safe_load, adhering to security best practices for parsing configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:43 PM