ClawHub
Back to skill

Security audit

Web Search By Searxng

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward SearXNG web-search helper, but users should trust the configured search server because queries are sent to it.

Install only if you are comfortable sending searches to the configured SearXNG instance. Prefer a trusted HTTPS or self-hosted instance, and avoid putting secrets, private project names, or sensitive investigative terms into searches on public instances.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documents capabilities that require network access and use of an environment variable, but it does not declare any explicit tool scope such as allowed tools or permissions. This weakens policy enforcement and user visibility, making it easier for the skill to perform outbound requests or access configuration sources without clear authorization boundaries.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill asks for or uses a user-provided/configured SearXNG instance URL but does not clearly warn that search queries and parameters will be transmitted to that remote server. Because queries may contain sensitive user interests, internal terms, or investigative prompts, this omission can lead to unintended privacy disclosure, especially when public or untrusted instances are used.

Missing User Warnings

Low
Confidence
80% confidence
Finding
This code performs a network request that sends the user-provided search query and optional parameters to an external SearXNG server. Although the file documents how to use the API, it does not include any explicit user-facing warning or disclosure about transmitting potentially sensitive search terms to a remote service.

Static analysis

No suspicious patterns detected.