new-skill
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts located at
fdk/tools/new-skill.py,harness/scripts/sync-skills.py, andharness/scripts/skill-registry.pyto automate the creation and synchronization of skill files. - [COMMAND_EXECUTION]: The instructions involve interpolating user-provided inputs such as the skill name, loop type, and description directly into shell commands. While this represents a surface for command injection if inputs are not sanitized by the platform, it is the primary intended functionality of this scaffolding tool.
Audit Metadata