design-tokens
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads external data from
.design/*/DESIGN_BRIEF.mdand uses it to generate configuration files. - Ingestion points: Process step 2 reads project-specific design briefs to derive token values.
- Boundary markers: No delimiters or specific instructions are provided to the agent to ignore potentially malicious embedded instructions within the design brief files.
- Capability inventory: The skill performs file system write operations to sensitive configuration files including
tailwind.config.js,tokens.css, andtheme.ts/theme.js. - Sanitization: No sanitization or validation steps are defined for the content extracted from the design brief before it is interpolated into the generated output.
Audit Metadata