React Nextjs Generator

• Outcome: Review
• Latest audit: May 28, 2026 · 10:34 AM UTC
• Version: 1.0.0

Overview

This is a real Next.js project generator, but it runs local project-generation tooling and writes files with weak path scoping and input validation.

Install only if you are comfortable with it creating files and running npm tooling locally. Use a fresh, isolated output directory, avoid requirements containing ../ or absolute-path-like routes/component names, and inspect generated files before running the app.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly directs use of `exec` to run a local script and `write` to save user-supplied requirements to a temporary file, but it provides no warning, approval step, or safety constraints around these side effects. In an agent setting, subprocess execution and filesystem writes expand the attack surface substantially because untrusted input may influence code generation or command behavior, and the user may not realize the skill will perform local actions.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README states the skill will automatically generate a complete React/Next.js project, which implies writing many files into the user's workspace, but it does not warn about file creation, overwrite risk, target directory handling, or confirmation requirements. In an agent context, missing disclosure about filesystem side effects can lead users to invoke the skill without understanding that existing files or directories may be modified or replaced.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill explicitly instructs the agent to generate a project structure, configuration files, pages, and components, which implies creating or modifying files, but it does not warn the user or require confirmation before doing so. In an agent environment, this can lead to unexpected workspace changes, overwriting existing content, or broad file generation beyond the user's intended scope.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill explicitly instructs the agent to invoke a local shell script that creates a full project, which implies filesystem writes and potentially broad changes to the user's workspace, but it provides no warning, confirmation step, scope limitation, or output directory constraints. This is dangerous because users may trigger unintended local modifications, overwrites, or side effects without understanding that the skill performs write operations beyond simple analysis.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: Routes extracted from an untrusted requirements document are converted into path segments and written directly to disk without normalization or traversal checks. An attacker could supply values such as '../' sequences or absolute-like paths to cause file creation outside the intended project directory, potentially overwriting arbitrary files accessible to the process.

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.