ClawHub
Back to skill

Security audit

Searxng Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward SearXNG search connector, but searches go to the endpoint the user configures.

Install only if you trust the SearXNG instance you configure, preferably over HTTPS for remote servers. Avoid searching secrets or confidential project data, and merge or back up any existing mcporter config before copying this package's config.json.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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 (2)

Tainted flow: 'url' from os.environ.get (line 79, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
url = f"{SEARXNG_URL}/search?q={encoded_query}&format=json"
    
    try:
        with urllib.request.urlopen(url, timeout=30) as response:
            data = json.loads(response.read().decode('utf-8'))
            results = data.get('results', [])[:limit]
            return results
Confidence
89% confidence
Finding
with urllib.request.urlopen(url, timeout=30) as response:

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill documentation describes capabilities that use environment variables, network access, and shell commands, but it does not declare corresponding permissions. This creates a trust and transparency gap: agents or users may invoke a skill with broader runtime access than expected, increasing the chance of unintended outbound requests, misuse of sensitive environment configuration, or shell-based abuse if the implementation is unsafe.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.