team-combat
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust orchestration workflow that partitions tasks among specialized subagents, minimizing the risk of a single agent having excessive authority or scope.
- [SAFE]: Strong human-in-the-loop controls are maintained by requiring explicit user approval via the AskUserQuestion tool at every critical phase transition (Design, Architecture, etc.).
- [SAFE]: File system interactions and configuration reads are restricted to specific, localized project directories such as design documents and internal technical preferences, reducing the attack surface.
- [SAFE]: The skill includes comprehensive error recovery protocols that surface blockers to the user immediately rather than attempting to proceed with unvalidated or failed subagent outputs.
Audit Metadata