ClawHub
Back to skill

Security audit

Agent Browser Clawdbot 0.1.0

Security checks across malware telemetry and agentic risk

Overview

This is a coherent browser automation skill, but it needs review because it encourages saving and reusing login/session data without enough safety guidance.

Install only if you trust the external agent-browser CLI and need agent-controlled browsing. Use test or least-privilege accounts where possible, treat saved auth state, cookies, and storage values like passwords, keep them out of shared folders and repositories, delete them after use, and require explicit confirmation before purchases, account changes, public posts, or other irreversible actions.

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
91% confidence
Finding
The skill explicitly recommends saving and loading browser auth state, which typically contains cookies and storage-backed session material, but provides no warning that these files are sensitive secrets. In an AI-agent setting, this increases the chance that session artifacts are stored insecurely, reused across tasks, or exposed to other users/processes, enabling account takeover or unintended cross-session access.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents commands for reading and modifying cookies and browser storage without any warning that these mechanisms often contain authentication tokens, CSRF values, PII, and other sensitive application data. In a headless automation skill intended for agents, exposing these capabilities without guardrails makes accidental exfiltration, logging of secrets, or unsafe manipulation of authenticated sessions more likely.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.