skills-create
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a development framework, promoting security through structured validation and progressive disclosure.
- [COMMAND_EXECUTION]: Benign use of shell commands like mkdir and cp for project scaffolding and file management within the agent's local directory.
- [DATA_EXFILTRATION]: No network activity or external data transfer mechanisms were found in the skill's logic or resources.
- [PROMPT_INJECTION]: Instructions focus on structural guidance and do not attempt to manipulate the agent's core safety behavior.
Audit Metadata