micro-skill-creator
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a meta-tool for generating skill templates. It does not contain any active code, script execution, or network operations.
- [PROMPT_INJECTION]: No patterns associated with prompt injection, safety bypasses, or instructions to ignore system guidelines were found. The instructional language is strictly focused on the task of skill creation.
- [DATA_EXFILTRATION]: No sensitive file paths, environment variable access, or hardcoded credentials are present. The skill does not perform any network requests to external domains.
- [REMOTE_CODE_EXECUTION]: There are no commands that download or execute remote scripts. References to external tools and frameworks (e.g., ruv-swarm, agent-creator) are descriptive of integration capabilities rather than active execution patterns.
- [COMMAND_EXECUTION]: The skill includes examples of slash command bindings using placeholders (e.g., ${file_path}), which is a standard feature for agent integration and does not represent an unauthorized command execution risk in this context.
Audit Metadata