product-design
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill does not contain any malicious patterns, prompt injections, or unauthorized data access attempts. Its instructions are strictly focused on product design methodology and quality standards.
- [NO_CODE]: The skill is composed entirely of markdown instructions, JSON evaluation files, and reference guidelines. It does not include executable scripts, shell commands, or binary files, significantly reducing its attack surface.
- [EXTERNAL_DOWNLOADS]: The skill references external documentation and design guidelines from trusted organizations such as the W3C (WCAG), Nielsen Norman Group (NN/g), Apple (Human Interface Guidelines), Google (Material Design), and the UK Government (GOV.UK). These references are used for educational purposes and do not involve code execution or software installation.
- [DATA_EXFILTRATION]: There are no indicators of network operations or attempts to access sensitive local files (e.g., credentials, environment variables). The skill's logic is confined to processing user-provided design contexts.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied design briefs (a standard ingestion surface), it lacks the capabilities (such as file-writing or command execution) to translate malicious input into a system compromise. It functions primarily as a decision-support layer for design professionals.
Audit Metadata