figma-implement-design

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: A detailed review of the instructions, scripts, and configuration files found no evidence of malicious patterns, such as command injection, privilege escalation, or data exfiltration.
  • [EXTERNAL_DOWNLOADS]: The skill is configured to connect to the official Figma MCP server at https://mcp.figma.com/mcp to fetch design context and assets. This targets a well-known service domain and is consistent with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external Figma files, which presents a potential surface for indirect prompt injection.
  • Ingestion points: External Figma design specifications and metadata are ingested via the get_design_context and get_metadata tools as described in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are used to distinguish design properties from agent commands.
  • Capability inventory: The skill uses MCP tools to read design data and instructions to generate code within the user's project repository.
  • Sanitization: There is no evidence of content validation or sanitization for the data retrieved from the Figma API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 09:46 AM
Security Audit — agent-trust-hub — figma-implement-design