apply-design-system
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
use_figmatool to execute JavaScript snippets for querying and modifying Figma documents. This is a primary function of the skill but involves running code in the Figma plugin environment.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to its reliance on external data from Figma designs.\n - Ingestion points: Metadata, component names, and property keys are retrieved using
get_metadataanduse_figmafrom the target Figma file (SKILL.md).\n - Boundary markers: The instructions lack delimiters or constraints to prevent the agent from following instructions potentially embedded in design components or text layers.\n
- Capability inventory: The skill can perform complex modifications to Figma files, including importing components and swapping instances via
use_figmaandimportComponentByKeyAsync(SKILL.md).\n - Sanitization: No input validation or sanitization is performed on the data retrieved from the design system or target frame before it is used to drive the workflow logic.
Audit Metadata