claude-subagent-creator
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and documentation-based, providing a workflow for generating subagent configuration files.
- [DATA_EXPOSURE]: No sensitive data exposure or exfiltration patterns were found. The skill mentions standard project and user configuration paths (e.g.,
.claude/agents/) which are the legitimate locations for subagent definitions in the platform context. - [COMMAND_EXECUTION]: The skill does not contain or generate executable shell commands. It describes the process of writing Markdown files to specific directories as part of its primary function.
- [PROMPT_INJECTION]: No prompt injection or behavior override patterns were detected. The skill actually provides guidance on how to write clear system prompts and descriptions to ensure reliable agent behavior.
- [REMOTE_CODE_EXECUTION]: There are no network operations, external downloads, or runtime code execution patterns.
Audit Metadata