skill-writer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides templates for creating well-structured SKILL.md files and directory structures.
- [COMMAND_EXECUTION]: Includes standard shell commands for directory management (mkdir -p) and file inspection (ls, cat) within the user's home directory or local project folder. These are used for the legitimate purpose of skill creation and debugging.
- [REMOTE_CODE_EXECUTION]: Contains a placeholder example for dependency installation (pip install package-name) within a markdown documentation block. It does not execute any remote scripts or download unverified packages.
- [DATA_EXPOSURE]: References standard paths for agent configuration (~/.claude/skills/) but does not attempt to access sensitive credentials or exfiltrate data.
Audit Metadata