validating-design-tokens
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard command-line utilities including
ls,grep, andsortto identify design token definition files and scan the codebase for hardcoded CSS properties and React inline styles. - [EXTERNAL_DOWNLOADS]: The instructions suggest installing
stylelintandstylelint-declaration-strict-valuevianpm. These are widely recognized and reputable open-source tools used for maintaining code quality and consistency in CSS development. - [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection because it processes untrusted data from the local codebase. * Ingestion points: Scans project files with
.css,.scss,.tsx, and.jsxextensions in thesrc/directory (SKILL.md). * Boundary markers: None are explicitly defined in the instructions to separate code content from instructions. * Capability inventory: Read-only file system access vialsandgrep, plus package installation capability vianpm(SKILL.md). * Sanitization: File contents are matched against regular expressions and reported to the user without prior sanitization or escaping.
Audit Metadata