beo-planning
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes specialized local CLI tools (
brandbv) for task management and dependency graphing. It also directs the agent to execute compilation commands during the discovery phase to verify code annotations, which is standard procedure in a software development environment. - [PROMPT_INJECTION]: The discovery and planning process involves processing requirements from
CONTEXT.mdand researching the local codebase. While this represents an indirect prompt injection surface, the risk is mitigated by the structured artifact workflow and the requirement for explicit user approval before execution begins. - [EXTERNAL_DOWNLOADS]: The skill mandates verifying external dependency versions against authoritative registries or sources of truth. This is a read-only validation step intended to ensure environment integrity and prevent supply chain attacks, which is a defensive measure.
Audit Metadata