skills/ghalex/skills/nextjs-rules/Gen Agent Trust Hub

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]: Running pnpm dlx involves 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/ and src/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
Risk Level
SAFE
Analyzed
Aug 13, 2026, 02:34 PM