skill-crafter
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill functions as a design framework and instructional guide. It contains no executable scripts (Python, Node.js, Shell, etc.), binary files, or automated system commands, posing no risk to the local environment.
- [NO_CODE]: There is no code shipped with this skill. Its functionality is entirely defined by Markdown instructions and YAML configuration for the purpose of guiding the user or the agent in creating better prompts.
- [EXTERNAL_DOWNLOADS]: All external links in the documentation point to the author's GitHub repository or legitimate image hosting for the project's banner. No unverified remote code patterns or suspicious download/execute chains were detected.
- [PROMPT_INJECTION]: The instructions do not contain any attempts to override system prompts, bypass AI safety guardrails, or use deceptive role-play techniques. The content is pedagogical and focuses on improving agent reliability through structured design.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found. The skill's 'Reviewer' pattern documentation explicitly provides checklists that teach users to identify and remove hardcoded secrets in their own projects as a best practice.
Audit Metadata