helm-arbiter
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill is configured with the
Bashtool in its allowed tools list. The instructions indicate its use for task execution and reporting, which is consistent with its stated purpose of managing project documentation. - [EXTERNAL_DOWNLOADS]: The skill utilizes
WebFetchandWebSearchtools. These are employed for gathering context and generating reports. No unauthorized or suspicious third-party domains are hardcoded in the instructions. - [PROMPT_INJECTION]: The skill is designed to ingest project documentation (e.g., original briefs, sprint planning docs). While this presents a theoretical surface for indirect prompt injection, the skill includes structured decision frameworks that guide the model's behavior, reducing the risk of accidental obedience to embedded instructions.
Audit Metadata