skill-development
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: Orchestrates the execution of local repository scripts, including bash and Python utilities, to perform automated linting and qualitative validation of new skills. Evidence: linting/lint-skill.sh, validation/validate-skill.sh, and scripts/lint_skills.py.
- [EXTERNAL_DOWNLOADS]: References the markdownlint-cli2 package from the public NPM registry to verify markdown standards during the linting phase.
- [SAFE]: Implements secure test-drive procedures by creating disposable workspaces with automatic cleanup traps, preventing changes to the primary repository during live scenario execution.
- [SAFE]: The skill processes user-supplied variables, such as skill names, which are incorporated into shell commands. This is an expected pattern for a developer-oriented tool. Ingestion points: skill name placeholders in SKILL.md. Boundary markers: none explicitly documented. Capability inventory: bash, mkdir, and git commands. Sanitization: none explicitly present in the provided markdown.
Audit Metadata