design-md

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The skill is designed to ingest and analyze external HTML content retrieved via web_fetch from project-provided URLs (htmlCode.downloadUrl).
  • Ingestion points: SKILL.md instructs the agent to download and parse HTML code from project metadata to extract design tokens.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore natural language commands embedded within the fetched HTML or CSS comments.
  • Capability inventory: The skill utilizes the Write tool to generate a DESIGN.md file and has web_fetch capabilities.
  • Sanitization: No sanitization or validation of the external HTML content is performed before analysis.
  • Data Exposure & Exfiltration (LOW): The skill uses web_fetch to access URLs dynamically provided by the Stitch MCP server. While this is necessary for its function, it creates a surface for network operations to non-whitelisted domains if a project's metadata is maliciously crafted.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 08:17 AM