ClawHub
Back to skill

Security audit

Chrome Web Automation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent browser-automation guide for a user's existing Chrome session, with no executable payload or hidden installation behavior.

Install only if you want the agent to work inside your existing Chrome session. Before invoking it, close or move away from sensitive tabs and give precise instructions for any clicking, typing, or form submission on logged-in sites.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill clearly states it operates in the user's live Chrome session, but it does not warn that actions may affect active tabs, authenticated sessions, visible page state, or sensitive data present in the browser. This can lead to unintended interaction with private content or stateful accounts if invoked without explicit user awareness and confirmation.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Guardrails
- Re-snapshot when element references go stale.
- Do not assume current tab state without checking.
- Prefer explicit browser actions over ambiguous natural-language leaps.

## Example Requests
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.