design-systems-frontend-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from external sources, such as UI mockups, screenshots, and product requirements, to generate design system documentation and frontend architecture guidance.
- Ingestion points: User-provided mockups, screenshots, UX flows, and product requirements are processed to create system rules and component contracts (as specified in
SKILL.md). - Boundary markers: The instructions do not implement or recommend the use of clear delimiters or instructions to disregard any embedded commands within the ingested content.
- Capability inventory: While the skill does not directly execute shell commands, it generates implementation guidance and architectural decisions that could be influenced by malicious content hidden in design metadata or content.
- Sanitization: The skill lacks explicit guidance on sanitizing or validating user-provided inputs for malicious patterns before processing them.
Audit Metadata