ClawHub
Back to skill

Security audit

Browser Automation Zh

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only browser automation helper; its risky browser actions are visible and aligned with its stated purpose, but users should tightly control scraping, logins, screenshots, and form submissions.

Install only if you want the assistant to operate a browser for clearly specified tasks. Use it on sites and accounts you are authorized to automate, avoid giving the agent passwords directly, confirm before submitting forms or making account changes, and store screenshots or scraped data only in approved locations.

SkillSpector

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

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description is extremely broad and packed with generic browser automation, scraping, testing, monitoring, and form-filling keywords, which can cause the skill to activate for a wide range of unrelated or higher-risk requests. In an agent environment, overbroad triggering increases the chance the skill is selected for sensitive actions such as login automation, mass scraping, or interaction with third-party sites without appropriate policy checks.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The usage examples endorse broad operational behaviors like scraping e-commerce listings, logging into backend systems, and bulk form submission without stating prerequisites, ownership, consent, or safety boundaries. That makes unsafe activation more likely and normalizes potentially abusive or policy-sensitive automation in contexts involving credentials, private systems, or third-party websites.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.