skill-composer
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a transparent orchestrator for agent skill development, using standard tools for task management and file manipulation.
- [COMMAND_EXECUTION]: Uses 'Write' and 'Edit' tools to create and update 'SKILL.md' files in specific local directories ('.claude/skills/' or 'skills/'). These operations are consistent with the skill's primary purpose and do not involve system-level or privileged execution.
- [EXTERNAL_DOWNLOADS]: Invokes secondary internal skills ('example-skills:skill-creator' and 'skill-reviewer') using the 'Skill' tool. These references target local or trusted internal capabilities and do not involve downloading or executing code from unverified external sources.
Audit Metadata