figma-create-design-system-rules

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the creation of project-level instruction files (such as CLAUDE.md or .cursor/rules/) based on external data fetched from a Figma MCP server. This creates an indirect prompt injection surface where a malicious Figma design file could potentially embed instructions that become part of the agent's permanent system rules.
  • Ingestion points: Data is ingested through the Figma MCP server tools: create_design_system_rules, get_design_context, and get_metadata in SKILL.md.
  • Boundary markers: The skill does not implement clear boundary markers or instructions for the agent to ignore embedded commands within the fetched design data.
  • Capability inventory: The skill allows the agent to read the codebase and write generated rules to local files (e.g., CLAUDE.md, AGENTS.md, .cursor/rules/).
  • Sanitization: No sanitization or validation of the Figma-provided data is specified before it is used to generate the final rule files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 10:27 PM