ClawHub
Back to skill

Security audit

neon

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Neon overview and routing skill with some broad triggers and tool-install guidance, but no hidden, destructive, or exfiltrating behavior in the artifact.

Before installing, be aware that this skill may activate for generic backend or database requests and may recommend installing or updating Neon tooling, sometimes globally. Review npx commands before running them, and use --no-env-pull if you do not want Neon environment variables written into local .env files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases include very broad terms such as "postgres", "database", "backend", "S3", and "call an LLM", which are common across many unrelated tasks. In an agent-skill routing system, this can cause the Neon overview skill to activate too often, hijacking requests that should be handled by more specific or safer skills and increasing the chance of inappropriate guidance or tool use.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.