nextjs-implementation
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard project validation commands such as linting, type checking, and build processes (e.g.,
npm run lint,npm run build). These are expected behaviors for a development-focused skill and are limited to the user's local project context. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes existing project files and user-provided prompts to generate code.
- Ingestion points: Project files (components, layouts, hooks, types) and user prompts.
- Boundary markers: None explicitly defined in the instructions, though it mandates following existing project conventions.
- Capability inventory: File system access (read/write) and execution of local build/lint tools.
- Sanitization: Relies on standard LLM guardrails; no specific sanitization logic is described for external data interpolation.
Audit Metadata