ClawHub
Back to skill

Security audit

Searxng Web Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward SearXNG web-search helper with some documentation gaps, not evidence of harmful behavior.

Install only if you operate or trust the SearXNG instance you point SEARXNG_URL at. Use HTTPS for non-local endpoints, avoid putting secrets or highly sensitive text into search queries, and be aware that this artifact references a missing scripts/search.clj file, so it may not work as packaged until that script is supplied.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is extremely broad ('search the web' for current information, research, documentation, fact verification, or anything beyond the model's knowledge), which can cause the agent to invoke this skill for a very wide range of requests. Over-broad activation increases the attack surface for prompt-injection delivered through untrusted web content and may bypass more specialized or safer skills that should handle narrower tasks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The API guide’s example requests use plain HTTP to send search queries, but it does not warn that queries and returned content may be exposed to network observers or modified in transit. In a web-search skill, queries can contain sensitive research topics, credentials accidentally pasted by users, or other private data, so normalizing insecure examples increases the chance of confidentiality and integrity loss.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The options specify language with a default of en, which creates a locale preference in the skill's natural-language behavior. The documentation does not indicate that the user can opt into other defaults or explain why English is required as the default locale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.