subagents-and-teams
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown documentation and reference guides for the Claude Code tool. It details features such as subagents, agent teams, and permission modes (e.g., default, acceptEdits, dontAsk, delegate, bypassPermissions, and plan). All provided examples are educational in nature and include security-oriented patterns, such as read-only validation scripts to prevent SQL injection or unauthorized write operations. No executable scripts, obfuscated content, or malicious instructions were identified within the provided files.
Audit Metadata