ClawHub
Back to skill

Security audit

Claude Chrome

Security checks across malware telemetry and agentic risk

Overview

The skill is a browser automation guide, but it tells users to run Claude with broad auto-approval in a real Chrome session, which needs careful review before use.

Install only if you intend to let Claude Code control Chrome noninteractively. Use a dedicated Chrome profile or test account, avoid sensitive logged-in sessions, keep prompts narrow and low-impact, monitor or stop background `claude` processes, and prefer safer built-in browser tools for simple read-only browsing.

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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly recommends `--dangerously-skip-permissions` and states it is 'required for automation,' which removes interactive approval barriers for browser actions. In a browser automation context, this can allow automated navigation, clicks, form submission, and potential access to sensitive authenticated web content without meaningful user confirmation, increasing the risk of data exfiltration or unintended destructive actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.