subagent-teams
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation and orchestration framework for parallel agent tasks. It contains no executable scripts or binaries that could perform unauthorized actions.\n- [SAFE]: No obfuscation, prompt injection, or hardcoded credentials were detected in the skill files or prompt templates.\n- [SAFE]: References to permission modes (e.g., 'dontAsk', 'acceptEdits') and memory scopes (e.g., '~/.claude/agent-memory/') accurately describe standard platform configurations for controlling agent autonomy and data persistence.\n- [SAFE]: The prompt templates provided for research and exploration tasks include explicit 'Do NOT modify any files' constraints, demonstrating a security-conscious design for automated subagent workflows.
Audit Metadata