chatbot-template

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a project template from the official shadcn-ui GitHub repository (github.com/shadcn-ui/chatbot-template.git). This is a well-known and recognized source for web development templates.
  • [COMMAND_EXECUTION]: Utilizes standard developer tools including git for repository cloning, pnpm for package management, and the vercel CLI for environment configuration.
  • [PROMPT_INJECTION]: The skill scaffolds a system with an indirect prompt injection surface.
  • Ingestion points: External data enters the agent context via the web_search and github_repo tools, processed in app/api/chat/route.ts.
  • Boundary markers: The template uses the Vercel AI SDK's structured tool-calling and typed UI parts to separate data types.
  • Capability inventory: The system includes tools for web searching, GitHub lookups, and file system access as defined in the allowed-tools (Bash, Read, Write, Edit).
  • Sanitization: The skill provides a 'Harden before public traffic' section (Step 7) advising the implementation of rate limiting and authentication to secure the endpoint.
  • [SAFE]: Instructions direct the user to manage environment variables via .env.local or the vercel env pull command, which aligns with industry best practices for local secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 06:45 AM
Security Audit — agent-trust-hub — chatbot-template