ClawHub
Back to skill

Security audit

Agent Browser Ref

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward browser automation reference, but users should handle saved auth state, cookies, and browser storage as sensitive secrets.

Install only if you trust the external agent-browser CLI and need browser automation. Treat saved auth state files, cookies, and localStorage values like passwords: keep them out of repositories and logs, use task-specific sessions, and delete saved state when it is no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly recommends saving and loading browser auth state to skip login flows, but provides no warning that the saved state file can contain sensitive cookies, tokens, and local/session storage data. In an agent setting, this can lead to accidental persistence, reuse, or exfiltration of active authenticated sessions if the file is stored insecurely or shared across tasks/users.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill documents commands to read and modify cookies and browser storage without any guidance on handling sensitive values. Because cookies and localStorage often contain session identifiers, CSRF tokens, or other secrets, an agent using these commands may expose credentials in logs, outputs, or persistent artifacts, or alter state in unsafe ways.

Skill Enumeration

Medium
Category
Agent Snooping
Content
# agent-browser-ref

Ingested on 2026-07-23T00:55:34Z from /root/.openclaw/workspace/skills/agent-browser-clawdbot/SKILL.md.

- source file: `SKILL.md`
- size: 5548 bytes
Confidence
96% confidence
Finding
skills/agent-browser-clawdbot/SKILL.md

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.