ClawHub
Back to skill

Security audit

Browse AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Browse AI connector that uses OOMOL's oo CLI and does not contain hidden scripts or scanner-supported malicious behavior.

Install only if you intend to let an agent operate Browse AI through your OOMOL-connected account. Review payloads before write actions, especially cookie updates, and be aware that starting robot tasks may use your Browse AI/OOMOL account resources.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.