claude-subagent-development
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate technical documentation and automation tools for subagent development. No malicious patterns, data exfiltration, or unauthorized network operations were detected.
- [COMMAND_EXECUTION]: The utility scripts
scripts/create-subagent.shandscripts/validate-subagent.shperform local file operations such as directory creation, template copying, and text parsing. These scripts use input validation (e.g., regex checks on subagent names) to prevent command injection and restrict operations to the expected project configuration directories. - [PROMPT_INJECTION]: The skill includes guidance on how to write effective subagent descriptions and system prompts. This content is focused on the intended functionality of the platform (subagent discovery and task delegation) and does not contain instructions to override safety filters or bypass core agent constraints.
Audit Metadata