design-research
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration risks were detected. The skill's instructions are consistent with its stated purpose of assisting in UI/UX research.
- [NO_CODE]: The skill is composed exclusively of Markdown instructions and does not contain any scripts, binaries, or automated code execution mechanisms.
- [EXTERNAL_DOWNLOADS]: The skill references various well-known services and marketplaces for design templates, including Shopify, Vercel, and Tailwind Labs. These references are for manual or agent-assisted research and do not involve the execution of remote scripts.
- [PROMPT_INJECTION]: The design research workflow involves analyzing external content from third-party marketplaces, which presents a surface for indirect prompt injection. 1. Ingestion points: External template marketplaces and demo URLs (e.g., ThemeForest, Webflow, Shopify). 2. Boundary markers: Absent. The skill does not instruct the agent to ignore instructions embedded within the analyzed templates. 3. Capability inventory: The skill itself does not employ executable tools, though the agent's general environment may permit file operations and code generation. 4. Sanitization: Absent.
Audit Metadata