design-taste-skill-pack
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes an untrusted "user brief" to determine visual direction and generate code. This represents an attack surface where malicious instructions embedded in the brief could attempt to influence the agent's behavior during the code generation process.
- Ingestion points: User design briefs are ingested in SKILL.md.
- Boundary markers: Absent; the instructions do not specify delimiters or explicit warnings to ignore instructions within the user brief.
- Capability inventory: Code generation for React and Next.js, and dependency installation suggestions (npm/yarn).
- Sanitization: Absent; the skill does not explicitly instruct the agent to filter or sanitize the content of the brief.
- [EXTERNAL_DOWNLOADS]: The component library files reference numerous external documentation pages and demos from well-known front-end services.
- References found in components/gsap-explore.md (GSAP, CodePen), components/aceternity-ui.md (Aceternity UI), components/21st-community.md (21st.dev), and components/reactbits.md (React Bits).
Audit Metadata