agent-module-frontend-ui-magic-shadcn

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard development commands such as npm install and npx shadcn@latest to initialize the project environment and install UI primitives. These are routine operations within the intended Next.js and Tailwind CSS development workflow.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of project dependencies from the NPM registry and UI component source code from the Shadcn registry and a Magic UI registry (via MCP tools). These downloads originate from well-known technology services and are documented as part of the primary functional purpose of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes component source code retrieved from an external registry via MCP tools (mcp_magic-ui_getRegistryItem). This represents an attack surface for indirect prompt injection if the source registry were compromised.
  • Ingestion points: Data returned by the mcp_magic-ui_getRegistryItem tool in Phase B.
  • Boundary markers: The instructions do not explicitly require the agent to use delimiters or perform safety audits on the retrieved code before writing it to the file system.
  • Capability inventory: The agent possesses capabilities to execute terminal commands (npm, npx) and write files to the local directory structure (components/ui/).
  • Sanitization: There are no explicit instructions for the agent to sanitize or validate the external code beyond ensuring it aligns with the requested component name.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:27 PM