figma-create-design-system-rules

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes a workflow for generating persistent rules for AI agents based on an analysis of the existing local codebase, which introduces an indirect prompt injection surface.\n
  • Ingestion points: Local source code files (e.g., components, styles, and architecture) are analyzed in Step 2 to determine project-specific conventions.\n
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' markers to ensure the agent distinguishes between architectural patterns and potential malicious instructions embedded within the analyzed files.\n
  • Capability inventory: The skill uses the 'create_design_system_rules' tool and performs file-write operations to sensitive agent configuration files including CLAUDE.md, AGENTS.md, and Cursor rules (.mdc files).\n
  • Sanitization: Absent. The skill does not prescribe validation or sanitization of the data extracted from the codebase before it is interpolated into the generated rule templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 12:28 PM