figma-integration
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of local scripts to fulfill its primary synchronization and validation functions.
- Evidence: Use of
scripts/figma/figma-pull.mjsandpython3 .claude/skills/_ux-ui-shared/scripts/validate_tokens.py(SKILL.md). - [INDIRECT_PROMPT_INJECTION]: The skill processes content from external Figma files (frames, variables, and screenshots), which creates a potential surface where malicious design data could influence agent behavior.
- Ingestion points: Reads Figma frames, variables, and screenshots via a connected Figma MCP server (SKILL.md).
- Boundary markers: Absent; no specific delimiters or instruction-ignore warnings are defined for the data ingested from Figma.
- Capability inventory: The skill can execute local Node.js and Python scripts and modify files within the
components/and.claude/directories (SKILL.md). - Sanitization: No sanitization or filtering logic is specified for the data pulled from the Figma API.
Audit Metadata