ClawHub
Back to skill

Security audit

Rapid Prototyper

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only rapid MVP-building skill whose cloud, analytics, feedback, and deployment guidance is disclosed and purpose-aligned, though users should review those defaults before using it.

Install this only if you want a fast, opinionated MVP workflow. Use test-scoped Supabase, Clerk, analytics, and Vercel projects; keep .env secrets out of source control; review package and deployment commands before running them; prefer preview deployments first; and strip or disable full-URL collection in feedback forms for sensitive apps.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad enough that the skill may activate for generic requests like 'build' or 'prototype' even when the user did not intend a speed-first MVP workflow. In this skill's context, unintended invocation is meaningful because the skill pushes fast deployment, analytics, and opinionated stack choices that can alter behavior in ways the user did not explicitly request.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs the agent to always add feedback collection, analytics, and deploy to a public URL, but it does not require a user-facing warning or consent checkpoint before enabling data collection or exposing a live deployment. In a rapid-prototyping context, this increases the risk of collecting user data without adequate notice and publishing insecure or unfinished apps prematurely.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The widget sends both free-form feedback and the full current page URL to '/api/feedback' without clearly informing the user that their location/context will be transmitted. URLs can contain sensitive information such as path-based identifiers, query parameters, invite tokens, reset links, or internal routing details, so silently exfiltrating them increases privacy and data-leakage risk; in a rapid-prototyping skill, the danger is higher because developers may copy this pattern verbatim into production-like apps without adding consent, minimization, or server-side filtering.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.