nextjs-rules
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
pnpm dlx shadcn@latest add <component>to integrate UI components. This uses the pnpm package manager to run the shadcn/ui command-line tool, which is a standard workflow for Next.js development.- [REMOTE_CODE_EXECUTION]: Runningpnpm dlxinvolves fetching and executing code from the npm registry at runtime. Since shadcn is a well-known service in the web development ecosystem, this is documented as standard project functionality.- [INDIRECT_PROMPT_INJECTION]: The skill processes project files during auditing and development, creating an ingestion point for untrusted data. \n - Ingestion points: Reads and audits project source files in
src/app/andsrc/components/. \n - Boundary markers: The instructions do not define specific delimiters to separate agent instructions from the content of audited files. \n
- Capability inventory: The agent has the capability to generate code, write files (copying
DESIGN.md), and execute shell commands (pnpm). \n - Sanitization: There is no mention of sanitizing or escaping the content of the files being audited.
Audit Metadata