ClawHub
Back to skill

Security audit

国内浏览器搜索终极增强

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Chinese web-search helper that sends user queries to public search engines and prints parsed results, with no evidence of hidden persistence, credential access, or unrelated system changes.

Install only if you are comfortable sending search terms to external search providers such as Bing, 360, and Zhihu. Avoid entering secrets, private customer data, confidential project names, or credentials as search queries, and make sure the curl.exe resolved from PATH is the trusted system binary.

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
93% confidence
Finding
The skill explicitly states it sends search requests to external search engines via curl, but it does not clearly warn users that their raw queries will be transmitted off-system to third parties. Search queries often contain sensitive personal, business, or investigative terms, so the omission creates a real privacy and data-handling risk even if the behavior is functionally expected for a search skill.

Natural-Language Policy Violations

Medium
Confidence
79% confidence
Finding
The skill forces an Accept-Language header of zh-CN,zh;q=0.9 for all outbound requests without user awareness or consent. This can leak or misrepresent user regional preferences, bias results toward Chinese-language content and infrastructure, and increase privacy/compliance concerns because the skill is explicitly steering traffic and content localization independently of user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.