writing-skills
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill employs authoritative instructions referred to as 'The Iron Law' to enforce specific documentation and testing workflows. These are used to maintain high quality in skill creation and do not attempt to bypass safety filters or ignore system constraints.
- [COMMAND_EXECUTION]: The documentation references the use of local tools such as a task manager CLI ('bd') and a local script ('render-graphs.js') for rendering diagrams. These tools are described as part of the local development environment.
- [DATA_EXPOSURE]: The skill identifies standard local directories used for storing agent-specific documentation (~/.claude/skills and ~/.codex/skills). There is no indication of unauthorized access to sensitive files or data exfiltration.
- [EXTERNAL_DOWNLOADS]: Mentions official guidance from Anthropic (anthropic-best-practices.md) and cross-references other skills (superpowers:test-driven-development), which are treated as trusted internal or well-known references.
Audit Metadata