converting-figma-designs
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from Figma designs, creating a potential surface for indirect prompt injection. \n- Ingestion points: Data is ingested via
get_design_context,get_metadata, andget_figjamtools (SKILL.md). \n- Boundary markers: The instructions do not provide delimiters or warnings to isolate design content from agent instructions. \n- Capability inventory: The agent has the ability to generate code and create configuration files based on the ingested content. \n- Sanitization: There is no explicit validation or sanitization of ingested strings from the Figma API.
Audit Metadata