Subagent System
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as documentation for a legitimate subagent system. It identifies standard local file paths for configuration, such as
.claude/agents/and~/.claude/agents/, which are used for storing agent definitions.\n- [SAFE]: A bash example is provided to illustrate manual file creation using thecatcommand. This snippet is benign, as it creates a Markdown configuration file locally and does not involve remote code execution, external downloads, or privilege escalation.\n- [SAFE]: The skill instructions were evaluated for prompt injection and behavioral overrides. No patterns were found that attempt to bypass AI safety filters, ignore system instructions, or exfiltrate sensitive data.
Audit Metadata