design-dna
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external URLs during the design analysis phase.
- Ingestion points: Visual design analysis fetches and processes content from user-provided URLs as specified in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or warnings to the agent to disregard potentially malicious instructions embedded within external design references.
- Capability inventory: The skill can generate self-contained HTML files containing JavaScript and CSS, and it is instructed to fetch and incorporate assets from original source URLs (SKILL.md, references/generation-guide.md).
- Sanitization: The workflow lacks explicit steps for sanitizing or validating external content before it is interpolated into the generated code.
- [DYNAMIC_EXECUTION]: The skill generates functional JavaScript and CSS code at runtime based on the analysis of reference designs and user-provided content, using predefined templates for effects like shaders and particle systems (references/generation-guide.md).
- [EXTERNAL_DOWNLOADS]: The skill fetches design assets from user-supplied URLs and loads animation and 3D libraries (Three.js, GSAP, Lottie) from well-known CDN services like JSDelivr.
Audit Metadata