figma-playwright-fallback
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the browser_evaluate tool to execute JavaScript snippets on the Figma web application. These scripts are used to automate UI tasks such as dismissing popups, navigating layer hierarchies, and triggering SVG exports.
- [DATA_EXFILTRATION]: Design properties including colors, layout dimensions, and SVG path data are extracted from Figma and returned to the agent context. This extraction is limited to the user's design workspace on the well-known figma.com service.
- [PROMPT_INJECTION]: The skill ingests untrusted data from third-party Figma designs (such as layer names and text content), creating a surface for indirect prompt injection. This is noted as an inherent risk of design-scraping tools rather than a detected exploit.
- [SAFE]: No evidence of credential exfiltration, persistence mechanisms, or unauthorized remote code execution was found. The skill's operations are transparent and consistent with its stated purpose.
Audit Metadata