skill-writing-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- NO_CODE (SAFE): The skill contains no executable scripts, shell commands, or automation logic. It is entirely composed of Markdown documentation and illustrative code snippets intended as examples for human or AI reference.
- PROMPT_INJECTION (SAFE): No patterns of instruction override, safety bypass, or role-play injection were detected. The instructions are strictly focused on documentation formatting and content standards.
- DATA_EXFILTRATION (SAFE): No network requests (curl, wget, fetch) or access to sensitive file paths (~/.ssh, .env, etc.) are present in the skill files.
- EXTERNAL_DOWNLOADS (SAFE): No external dependencies or remote scripts are referenced or downloaded. All rule references (e.g., @rules/...) are internal to the skill's directory structure.
- OBFUSCATION (SAFE): All content is written in clear, human-readable Markdown. No Base64 encoding, zero-width characters, or homoglyphs were found.
Audit Metadata