design-audit
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill demonstrates excellent security hygiene by establishing a strict separation between visual design changes and functional code logic. It includes a mandatory human-in-the-loop approval gate for every phase of implementation, preventing autonomous or unauthorized changes to the codebase.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from the project repository, including design documents (
DESIGN_SYSTEM.md), requirements (PRD.md), and source code files. While these ingestion points create a surface for indirect prompt injection, the risk is effectively mitigated by the skill's adherence to a phased plan and the requirement for user review of all proposed changes.
Audit Metadata