skill-creator
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily composed of markdown documentation and templates designed to guide the creation of other skills.
- [COMMAND_EXECUTION]: Includes several shell scripts and command-line examples in
validation.mdandnaming.mdfor validating skill metadata and directory structure. These scripts use standard Unix utilities (grep, awk, cut, test) and are restricted to the local.claude/skills/environment. - [DATA_EXPOSURE]: No access to sensitive files, environment variables, or credentials was detected. The validation logic is limited to reading metadata from markdown files within the skill directory.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any network operations or download external packages or scripts.
- [PROMPT_INJECTION]: Instructions are focused on file structure and documentation standards, with no attempts to bypass safety filters or override agent core behaviors.
Audit Metadata