design-system-guard
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and analyze untrusted external data such as theme files, CSS, Tailwind configurations, and source code. * Ingestion points: theme files, CSS variables, Tailwind configuration, component libraries, and target code as defined in SKILL.md. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed data are specified. * Capability inventory: The skill relies on standard agent capabilities for file reading and response generation. * Sanitization: No input validation or sanitization routines are defined for the analyzed data content.
- [SAFE]: The skill does not contain any executable scripts, remote downloads, obfuscated content, or persistence mechanisms. Its behavior is limited to providing natural language guidance for design audits.
Audit Metadata