create-design-system-rules

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch design data, screenshots, and image assets from the Figma MCP server. These operations are performed via standard tool calls to a trusted vendor (Figma) and are essential for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill requires calling the create_design_system_rules tool on the Figma MCP server to retrieve templates and foundational prompts. This is a standard and expected use of an MCP server.
  • [PROMPT_INJECTION]: The skill uses instructional markers such as 'IMPORTANT:' and 'Required Flow (do not skip)' to guide the agent in generating high-quality rules. These do not attempt to bypass safety filters or override system-level constraints; rather, they serve as formatting and quality control instructions for the task at hand.
  • [DATA_EXPOSURE]: The skill involves analyzing the local codebase (e.g., directory structures, styling files, and component organization) to tailor the generated rules. This is restricted to public project files (e.g., tailwind.config.js, src/components) and does not target sensitive user credentials or system secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 02:38 PM