ClawHub

web-searxng

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed SearXNG search helper with bounded local discovery and caching, not evidence of hidden or harmful behavior.

Install only if you are comfortable with the skill checking local Docker/localhost ports to find SearXNG and caching search results locally. For best control, set SEARXNG_URL to the exact SearXNG instance you trust and avoid highly sensitive queries unless you also control that instance and the local cache.

SkillSpector

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

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly states it will inspect environment variables, running Docker containers, and port mappings to auto-discover a local SearXNG service, but the issue notes the description does not provide a clear user warning about this local enumeration behavior. Inspecting local containers and mapped ports expands the skill's visibility into host configuration and may expose internal service metadata without informed user consent. In a search skill, this behavior is more dangerous because container and port discovery is not essential to the user's apparent task and can surprise users who expect only outbound web search.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
User search queries are sent over the network to the configured SearXNG instance, and on failure the code automatically generates a DuckDuckGo fallback URL containing the full query. In a skill context, queries may contain sensitive prompts or identifiers, so silently redirecting or exposing them to a third-party service creates a privacy leak and can violate user expectations.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal