design-inspiration-index
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a detailed routing map that encourages the agent to visit and interpret content from numerous external galleries, product UI examples, and documentation sites (e.g., landing.love, saaspo.com, refero.design, and the VoltAgent/awesome-design-md repository). This creates an attack surface where an adversary could embed malicious prompts in these third-party environments to influence the agent's logic.
- Ingestion points: Multiple external URLs listed in SKILL.md and references/galleries.md.
- Boundary markers: The instructions lack specific guidance or delimiters to prevent the agent from accidentally executing instructions found within these external design references.
- Capability inventory: The agent may use browser-based tools or network utilities to fetch this content, and is often encouraged to copy or adapt code (e.g., shadcn/ui components) into the local environment.
- Sanitization: No explicit sanitization of external site content is defined in the skill logic.
- [EXTERNAL_DOWNLOADS]: The skill recommends several external dependencies and code sources, including the VoltAgent/awesome-design-md repository and various third-party component libraries. While these are common in the design community, they represent unverifiable external resources that the agent is directed to rely upon.
Audit Metadata