ClawHub
Back to skill

Security audit

google-search-wsl

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed WSL Chrome helper for Google searches, with manageable browser-debugging and privacy caveats but no evidence of hidden or malicious behavior.

Install only if you want Google searches performed through a WSL Chrome instance. Avoid logging into important accounts in the debug profile, close Chrome or port 9222 when finished, and set GOOGLE_SEARCH_LANG if you do not want zh-CN-influenced results.

SkillSpector

By NVIDIA
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
Confidence
89% confidence
Finding
The manifest description is broad enough to activate on generic research, news, and information-retrieval requests, which can cause the skill to be invoked more often than a user would reasonably expect. Because the skill launches a real browser and sends queries to Google, over-broad activation increases the chance of unintended external data disclosure and browsing actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The instructions tell the agent to perform searches and retrieve pages from Google without warning that search terms, browsing activity, and fetched content will be transmitted to external services. This is dangerous because users may provide sensitive research topics, internal project names, or other confidential information that would be exposed off-system without informed consent.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The Chrome launch command forces the browser locale to zh-CN without documenting why or giving the user a choice. While not inherently malicious, changing locale can affect search results, language, content regionalization, and user expectations, which can mislead users or cause unintended routing of content through region-specific experiences.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal