Back to skill

Security audit

Bits Browser Automation

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed browser automation integration, but users should treat it as capable of acting on real websites and accounts.

Install only if you trust Bits and the npm package it launches. Keep the API key private, avoid committing MCP config files, rotate or revoke the key if exposed, and confirm before using the skill on real accounts, OAuth or 2FA flows, purchases, messages, admin panels, or other state-changing actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill advertises handling OAuth, login forms, 2FA, and stored credentials but does not warn users that browser automation may access or submit sensitive authentication data to third-party sites. In this context, omission of safety guidance is risky because users may invoke the skill for real accounts without understanding credential exposure, session misuse, or unintended privileged actions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The examples encourage filling and submitting web forms but provide no warning that automated browser actions can create accounts, send messages, place orders, or otherwise modify external systems and user data. Because this skill is specifically for live browser automation, the lack of guardrails increases the chance of unintended real-world side effects.

Session Persistence

Medium
Category
Rogue Agent
Content
1. Go to [app.usebits.com](https://app.usebits.com)
2. Sign in with Google
3. Navigate to **Settings → API Keys**
4. Click **Create API Key**, give it a name
5. Copy the key (starts with `bb_`) — you won't see it again

### 2. Configure MCP
Confidence
86% confidence
Finding
Create API Key**, give it a name 5. Copy the key (starts with `bb_`) — you won't see it again ### 2. Configure MCP Add to your MCP config (e.g., `~/.openclaw/openclaw.json`): ```json { "mcpServer

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.