ClawHub
Back to skill

Security audit

private-web-search-searchxng

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward self-hosted SearXNG search helper, with Docker and local search commands that match its stated purpose.

Before installing, make sure you are comfortable running a persistent local SearXNG Docker container on port 8080. Use the remove command only when you intend to delete that container, and remember that search queries still go from your SearXNG instance to selected upstream search engines.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Missing User Warnings

Low
Confidence
89% confidence
Finding
This markdown file includes a destructive management command, `docker rm searxng -f`, which force-removes the container. The surrounding documentation labels it as 'Remove' but does not explicitly warn that this deletes the local container state and may require re-creation or reconfiguration afterward.

External Script Fetching

High
Category
Supply Chain
Content
docker restart searxng

# Verify
curl -s "http://localhost:8080/search?q=test&format=json&engines=bing&num_results=1" | python3 -c "import sys,json; d=json.load(sys.stdin); print(f\"Results: {d.get('number_of_results',0)}\")"

## Usage
Confidence
90% confidence
Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.