prototype-to-figma-skill

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted data. \n
  • Ingestion points: Reads and analyzes external prototype source files in 'Step 2: Analyze Prototype Source'. \n
  • Boundary markers: None identified; instructions do not specify the use of delimiters or warnings to ignore embedded instructions. \n
  • Capability inventory: Includes file creation, frame creation, component instantiation, and metadata retrieval via the Figma MCP server. \n
  • Sanitization: No explicit sanitization or validation of the prototype code is mentioned before the analysis phase. \n- [COMMAND_EXECUTION]: The documentation provides instructions for users to execute shell commands to verify installation and configuration, specifically using 'cat' and 'grep' on application configuration files such as 'claude_desktop_config.json' and 'mcp_config.json'. \n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the '@figma/mcp-server', which is a well-known service package, and references a public GitHub repository for maintenance and issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 06:33 PM
Security Audit — agent-trust-hub — prototype-to-figma-skill