figma
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches design metadata and image assets from the official Figma REST API (api.figma.com). This interaction involves well-known official domains and is central to the skill's purpose.
- [COMMAND_EXECUTION]: Uses the standard CLI tools
curlandjqto perform network requests and process JSON responses. The logic is transparent and limited to API interaction. - [PROMPT_INJECTION]: The skill processes potentially untrusted content from the Figma API (such as file comments or layer text) which provides a surface for indirect prompt injection.
- Ingestion points: Data retrieved from api.figma.com/v1/files/ (SKILL.md).
- Boundary markers: None identified in the provided instructions.
- Capability inventory: Limited to read/write API operations using
curlandjq. - Sanitization: No specific sanitization or filtering logic is mentioned for processed API data.
Audit Metadata