figma-to-web
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill demonstrates secure credential handling by specifying that Figma API tokens must be injected via environment variables rather than being hardcoded or stored in cleartext.
- [SAFE]: Instructions include an explicit security-positive rule forbidding the use of lookalike characters (homoglyphs) for icons or text, which prevents spoofing and obfuscation attacks in the resulting web implementation.
- [SAFE]: All external references for Figma extraction and design system mapping target internal relative paths within the repository, ensuring the agent remains within a controlled execution environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Figma node URLs, which constitutes an ingestion point for untrusted content. The risk is mitigated by the skill's reliance on a deterministic shared extraction procedure and mandatory visual/accessibility verification steps.
Audit Metadata