ClawHub
Back to skill

Security audit

.Agent Browser Clawdbot.Disabled.20260401 112736

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed browser-automation skill with real session-data risks, but the access is purpose-aligned and user-directed.

Install only if you are comfortable giving the agent controlled browser-automation access. Prefer isolated sessions over your real Chrome profile, treat auth.json and saved session files like passwords, keep API keys in protected files, do not share or commit browser state, and delete persisted sessions when no longer needed.

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
95% confidence
Finding
The skill explicitly instructs users to save and load browser auth state and exposes commands for reading cookies and local/local storage, but it does not warn that these artifacts can contain session tokens, persistent authentication data, and other secrets. In an AI-agent context, this is especially risky because agents may store, echo, mishandle, or reuse these values across tasks or sessions, enabling account takeover or unintended cross-user access if the saved state files are leaked or reused improperly.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.