ClawHub
Back to skill

Security audit

Agent Browser Assistant

Security checks for vulnerabilities and agentic risk

Overview

This browser automation skill is mostly coherent, but it gives broad account-session, form-filling, file-upload, scraping, and export guidance without clear user-consent or scoping guardrails.

Review this skill before installing if you expect the agent to browse logged-in sites. Only allow use of your browser profile, credentials, local file uploads, screenshots, PDFs, or authenticated scraping when you have explicitly requested that action and trust the destination site.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly enables sensitive browser actions including login automation, form filling, file upload, and PDF export, but provides no warnings, consent requirements, or handling guidance for credentials, local files, or potentially sensitive page contents. In an agent setting, this increases the risk of accidental credential submission, exfiltration of local files, or capture/export of sensitive data from authenticated sessions.

Static analysis

No suspicious patterns detected.