bro-give-me-plan
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill strictly operates in a planning mode and explicitly forbids the generation of executable code, diffs, or patches within its plans, which significantly reduces the risk of malicious code injection or unintended execution.
- [SAFE]: A dedicated 'Implementation Hygiene' reference file is included, which mandates secure practices such as ensuring secrets are never stored in the repository, prohibiting direct schema changes on live databases, and requiring the use of existing project mechanisms for data migrations.
- [SAFE]: The plan review workflow includes a structured cycle involving independent review tools and 'closer' subagents, with built-in limits (maximum 10 attempts) to prevent infinite loops or resource exhaustion.
- [SAFE]: No evidence of obfuscation, unauthorized network communication, privilege escalation, or persistence mechanisms was found. All tool calls (e.g.,
/bro-review-spec-plan,CreatePlan) appear to be platform-integrated commands for the intended workflow.
Audit Metadata