Subagents Guide
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation guide for configuring 'Subagents' within the Claude Code ecosystem, focusing on task delegation and context preservation.- [SAFE]: Shell commands included in the documentation (e.g.,
mkdir -p .claude/agents) are intended for local directory structure setup for configuration files and do not perform unauthorized actions.- [SAFE]: The skill actively promotes security best practices, specifically the 'Principle of Least Privilege', by instructing users to limit tool access for subagents to only what is necessary for their specific tasks.- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, obfuscation, or unauthorized remote code execution were found in the skill body or metadata.
Audit Metadata