design-to-code-check
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Figma specifications and source code files, which is a standard surface for indirect instructions.
- Ingestion points: Figma node data via Figma MCP, Chromatic visual regression snapshots, and local or GitHub-hosted source code files.
- Boundary markers: No explicit delimiters or instruction-ignoring warnings are used when interpolating external design values or code snippets into the evaluation context.
- Capability inventory: The skill uses
Read,Write,Grep, and restrictedBashcommands (cat,find,head,ls,rg) to inspect implementation files. - Sanitization: There is no explicit evidence of sanitization or filtering for data retrieved from design nodes or source code comments before comparison.
Audit Metadata