ClawHub
Back to skill

Security audit

SearXNG Self-Host

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: installs or uses a self-hosted SearXNG search service, with disclosed server-level setup and disclosed external search fallbacks.

Install this only on a server or VM where you are comfortable making system-level changes. Review the shell script first, understand that it enables a persistent SearXNG service, and avoid sensitive search queries unless you are comfortable with them reaching upstream search providers or the Wikipedia/GitHub fallback.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill tells the user to run a root-level installation script that creates system users, writes to /etc, and starts a system service, but it does not warn about the security and operational impact of those changes. In an agent context, this is risky because it normalizes privileged execution and persistent system modification without requiring review, least-privilege controls, or rollback guidance.

External Transmission

Medium
Category
Data Exfiltration
Content
def search_github(query, count=5):
    """GitHub Search API - 10 req/min unauthenticated"""
    url = f"https://api.github.com/search/repositories?q={urllib.parse.quote(query)}&per_page={count}"
    req = urllib.request.Request(url, headers={**HEADERS, 'Accept': 'application/vnd.github.v3+json'})
    try:
        with urllib.request.urlopen(req, timeout=8) as r:
Confidence
93% confidence
Finding
https://api.github.com/

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.