dev-orchestrate-spec
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were identified. The skill follows best practices for AI agents by requiring user confirmation for all major transitions and enforcing read-only permissions during codebase research.
- [COMMAND_EXECUTION]: The skill uses local tools for building, linting, testing, and merging findings. These are standard operational tasks for a development orchestrator and are confined to the local project environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user prompts and repository context at several stages (Phase 1, Phase 2, and Review synthesis). It mitigates risks through explicit user confirmation gates, read-only research boundaries, and structured artifact generation (spec.md, plan.md). The capability to write code and execute tests is gated by human approval of the underlying implementation plan.
Audit Metadata