figma-implement-design

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data from Figma nodes via the get_design_context and get_metadata tools. This presents a surface for indirect prompt injection where malicious instructions could be embedded in Figma text layers or metadata. However, this is a low-risk surface as the skill's capabilities are limited to code generation and do not involve arbitrary command execution or external data exfiltration.
  • [SAFE]: The skill is authored by a trusted organization (OpenAI) and utilizes local communication with a Figma MCP server at http://127.0.0.1:3845/mcp. Instructions to modify local configuration files like ~/.config/kilo/kilo.json are standard for setting up the agent's environment and do not involve credential theft or sensitive data exposure. No obfuscation or malicious persistence mechanisms were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 02:29 PM