stitch-mcp-update-design-system

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a standard configuration file for the Model Context Protocol (MCP). It defines the parameters and usage for the update_design_system tool. No suspicious behaviors such as prompt injection, unauthorized network access, or remote code execution were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for ingesting external data into design system properties, which represents a potential surface for indirect injection.
  • Ingestion points: The designTokens and styleGuidelines fields in the update_design_system tool call accept arbitrary string input from processed content.
  • Boundary markers: No specific delimiters or boundary markers are defined in the instructions to isolate these inputs from the agent's control flow.
  • Capability inventory: The skill itself does not implement any dangerous capabilities; it only provides instructions for calling an external MCP tool whose implementation is outside the scope of this file.
  • Sanitization: No sanitization or validation logic for the provided design system strings is present within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 01:32 AM