web-design-expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest and process data from external sources such as Figma URLs and 21st.dev component search results. This data is then used to influence code generation and editing via MCP tools, creating a surface for potential injection if the source data is malicious.\n
- Ingestion points: references/tooling-integration.md (Figma URL data extraction and 21st.dev inspiration search).\n
- Boundary markers: None explicitly defined in the prompts to distinguish between instructions and data.\n
- Capability inventory: Write, Edit, mcp__magic__21st_magic_component_builder, mcp__magic__21st_magic_component_refiner.\n
- Sanitization: None described in the provided reference materials.\n- Dynamic Execution (LOW): The skill utilizes the mcp__magic__21st_magic_component_builder and mcp__magic__21st_magic_component_refiner tools to generate React and Tailwind CSS components at runtime. While this is the core intended purpose of the skill, it involves creating executable code from external inputs. Severity is low as this is the primary function.\n- No Code (SAFE): The skill package contains only Markdown documentation and configuration files. It does not include any local executable scripts or binary files.
Audit Metadata