command-development
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a meta-documentation file providing guidance on slash command development for Claude Code. It does not contain executable malicious code or instructions that bypass safety guidelines.
- [COMMAND_EXECUTION]: The skill documents the use of shell commands via the dynamic context injection syntax (!command). These are pedagogical examples (e.g., git diff, npm test, gh pr view, gh pr view) and fall under the security exception for documentation and tutorials.
- [PROMPT_INJECTION]: The content uses instructional language to explain platform behavior (e.g., 'Commands are Instructions FOR Claude') rather than attempting to subvert agent safety or bypass constraints.
- [EXTERNAL_DOWNLOADS]: The documentation mentions external tools and scripts (e.g., node, bash scripts) in the context of plugin development, but the skill itself does not initiate any remote downloads or execution from untrusted sources.
Audit Metadata