figma-implement-design
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts exclusively with Figma, a well-known service, and uses a local MCP server for asset retrieval. These operations are within the expected scope of the tool's functionality.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from an external source (Figma) to generate executable code.
- Ingestion points: External data enters the context through
get_design_contextandget_metadatatool calls inSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or warnings to ignore embedded instructions within the fetched Figma metadata or design context.
- Capability inventory: The agent has the capability to write files to the user's repository (creating or updating components as described in Step 5 and Step 6).
- Sanitization: There is no mention of sanitizing or validating the content returned by the Figma API before it is used to generate code.
Audit Metadata