skill-maker
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a meta-guideline for authoring and refining AI agent skills. It emphasizes quality control, context efficiency (Progressive Disclosure Principle), and rigorous testing (Red-Green-Refactor) to ensure agent compliance.
- [COMMAND_EXECUTION]: The skill allows the use of the 'Bash' tool, which is used for legitimate administrative tasks such as creating directory structures (e.g., 'mkdir -p dev-workflow/skills/...') and managing local files. No high-risk or obfuscated commands were found.
- [EXTERNAL_DOWNLOADS]: The skill does not define any remote URLs for downloading scripts or data. It describes a structure for 'Bundled Resources' which are intended to be local to the skill package.
- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override system-level constraints. While it uses strong language ('The Iron Law', 'No exceptions'), these are used to enforce a specific development methodology for the agent to follow when creating skills.
- [DATA_EXFILTRATION]: There are no patterns suggesting the collection or transmission of sensitive data. The 'allowed-tools' are appropriate for the described task of skill authoring.
Audit Metadata