design-system
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in audited websites or codebases.
- Ingestion points: The
auditfunctionality (Mode 2) accepts external URLs via the--urlparameter, and thegeneratefunctionality (Mode 1) uses a browser tool to research competitor websites. Additionally, the skill reads existing codebase files (CSS, Tailwind, styled-components) and PR content. - Boundary markers: The instructions do not define any specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the external content or code files.
- Capability inventory: The skill has the capability to write local files (
DESIGN.md,design-tokens.json,design-preview.html) and uses a browser tool for web navigation. - Sanitization: There is no mention of sanitization, filtering, or validation of the content retrieved from external URLs or local source code before it is processed by the agent.
Audit Metadata