ClawHub
Back to skill

Security audit

Agent Browser Core Temp

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent browser-automation guidance skill with disclosed safety controls; its main caution is one optional unpinned Playwright install command.

Install this skill only if you intend to use agent-browser for web automation. Run browser tooling in a dedicated low-privilege environment, pin the agent-browser version, prefer lockfile-controlled or pinned Playwright installation over the unpinned npx fallback, and require explicit approval before using credential, cookie, storage, proxy, file-access, eval, or custom-runtime features.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding
The documentation recommends `npx playwright install-deps chromium` without pinning a specific Playwright version, which can cause consumers to fetch and execute whatever package version `npx` resolves at runtime. In an agent-browser skill context, installation commands are high risk because they may run with substantial host privileges and can introduce supply-chain exposure or unexpected behavior changes over time.

Static analysis

No suspicious patterns detected.