figma-to-angular
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Figma URLs provided by users. This data is ingested via the
get_design_contexttool and used to generate component code. - Ingestion points: External Figma design data retrieved via
get_design_context(Phase 1). - Boundary markers: The instructions state that the retrieved code should be treated as a 'structural reference only', but there are no explicit delimiters or instructions to ignore embedded prompts within the Figma metadata.
- Capability inventory: The skill has capabilities to write files to the local file system (Phase 5) and interact with the browser via Playwright (Phase 6).
- Sanitization: No specific sanitization or validation of the fetched Figma content is mentioned before it is used to generate code.
Audit Metadata