ClawHub

NextJS

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Next.js helper with local project-memory behavior that fits its stated purpose, though users should understand what it may remember.

Install only if you are comfortable with the assistant keeping local notes about your Next.js stack, conventions, and deployment target. Do not store secrets in those notes, and review deployment, package-install, PM2, Docker, Vercel, or CI/CD commands before letting an agent run them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation criteria are overly broad: 'User needs Next.js expertise' covers a wide range of requests without clear exclusions or routing boundaries. In an agentic system, this can cause the skill to activate in contexts where it should defer to other skills or avoid acting, increasing the chance of inappropriate actions, overreach, or unsafe guidance being applied to adjacent domains like auth, deployment, or environment handling.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill instructs itself to determine within the first few exchanges whether it should 'jump in whenever you're working on Next.js,' which is broad and can trigger unsolicited engagement beyond explicit user requests. In an agent setting, ambiguous activation increases the chance of over-collection of context, inappropriate intervention, or actions taken without clear consent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The instruction to save behavior preferences to 'their main memory' introduces persistent storage of user data without any user-facing notice or consent flow. Even if the data seems operational, undisclosed persistence can violate user expectations and create privacy and retention risks across sessions.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly directs writing Next.js version, dependencies, deployment target, conventions, and project-specific patterns to local files under '~/nextjs/...', but it tells the agent to 'Start naturally' and not mention setup, which suppresses transparency. This combination makes the persistence behavior more dangerous because project metadata may be retained across sessions without the user's awareness.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal