subagents
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a 'lead-agent' pattern that centralizes control, integration, and final validation, preventing subagents from making unreviewed changes to a codebase.
- [SAFE]: It enforces strict isolation by requiring each subagent to work on a unique branch and stay within an 'owned files' list, which significantly reduces the risk of unintended system modifications.
- [SAFE]: The guidelines explicitly prohibit subagents from overriding safety filters or modifying security configurations by requiring them to inherit the lead agent's model settings by default.
- [SAFE]: No external downloads, obfuscation, or unauthorized network operations were found in the instruction files or configuration.
Audit Metadata