design-system-ai-agent
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains instructional content for a Design System AI assistant. Its instructions promote secure and standardized development practices, such as using semantic HTML, maintaining accessibility (ARIA, contrast), and adhering to project-specific dependencies and documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface by processing external files, screenshots, and documentation. However, it explicitly mitigates this risk in the 'Confirm Results and Report' section by instructing the agent that external attachments are only references and do not have authority over user requests or repository instructions. This is a best-practice guardrail for agents handling untrusted external content.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts, shell commands, or network-enabled tools that could be leveraged for malicious activity.
Audit Metadata