Security audit

Searxng Web Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward SearXNG web search skill, with ordinary privacy considerations because search queries go to the configured search server.

Install only if you have or trust the configured SearXNG instance. Avoid putting secrets or sensitive private information into search queries, and verify any separately supplied search script before running it because the documented script is not included in this artifact.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill description is very broad ('use when you need current information... look up anything beyond your knowledge'), which can cause the agent to invoke this skill for a wide range of prompts without clear necessity. Overbroad activation increases the chance of unnecessary external web requests, potentially exposing user queries to a network service and expanding the attack surface for prompt/data exfiltration through fetched content.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The 'When to Use' section lists many generic scenarios but does not define when the skill should not be used, making activation ambiguous. In an agent setting, this can lead to over-invocation of an external search tool, causing unnecessary data sharing with the SearXNG instance and increasing exposure to untrusted web content.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.