design-system-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on design token architecture, color ramp calculation, and accessibility standards with no evidence of malicious intent or unauthorized data access.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface related to importing external design tokens and provides mitigation guidance. 1. Ingestion points: DTCG token JSON files imported from external design tools or packages as described in the Security Guardrails. 2. Boundary markers: Explicit instructions to schema-validate and diff imported artifacts. 3. Capability inventory: File system writing and build execution allowed in metadata. 4. Sanitization: Explicit instructions to treat imported metadata as data rather than authoritative instructions.
Audit Metadata