ClawHub
Back to skill

Security audit

Agent Browser Cli.Bak

Security checks across malware telemetry and agentic risk

Overview

This is a browser automation skill with sensitive capabilities, but its artifacts describe those capabilities coherently and do not show hidden or destructive behavior.

Install only if you intend to let your agent operate a remote browser service. Avoid using it on accounts or pages with secrets unless necessary, confirm before submissions or purchases, and remember that screenshots plus stored browser sessions may contain sensitive data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger conditions are broad enough to overlap with many ordinary web-related requests, which can cause the skill to activate when the user did not clearly intend browser automation. In this skill's context, that is more dangerous because the documented actions include clicking, form filling, sign-ins, and screenshots, all of which can change account state or expose sensitive data if invoked unnecessarily.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents account-affecting and data-handling behaviors such as sign-in, form submission, cron-based automation, and screenshots, but it does not warn about credential handling, unintended submissions, persistent automation, or capture of sensitive on-screen information. In a browser automation skill, this omission materially increases risk because users may not realize actions are state-changing, recurring, or privacy-impacting.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.