t3-review-quorum
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a structured orchestration workflow that uses platform-native capabilities like
delegate_taskandorchestrator_capabilitiesto manage sub-agents. No unauthorized command execution or sensitive file access was identified. - [SAFE]: The skill's instructions focus on implementing a specific review mechanism, inheriting safety and scope boundaries from a referenced base skill. The use of local paths for documentation (e.g.,
~/.agents/skills/code-quorum/SKILL.md) is standard within the agent's operating environment. - [SAFE]: Data handling is limited to passing review rubrics and code to delegated tasks. The use of 'async' mode and 'inherit' runtime settings follows established patterns for parallelized AI workflows without introducing additional risk vectors.
- [SAFE]: No obfuscation, prompt injection attempts, or persistence mechanisms were found in the skill metadata or instructions.
Audit Metadata