human-ui-design
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external design references from the internet and internal backend schemas or existing UI code. Maliciously crafted data in these sources could potentially influence the agent's code generation.
- Ingestion points: External design websites (via web tools) and local project files including component files, backend schemas, and API documentation (referenced in the 'Workflow Wajib' section of SKILL.md).
- Capability inventory: Generation of complex frontend code including Tailwind CSS, React, Vue, Svelte, and Next.js components.
- Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore embedded instructions within the processed design references or schemas.
- Sanitization: Absent; there are no explicit instructions to sanitize or validate the content fetched from external inspiration sources before implementation.
Audit Metadata