ClawHub
Back to skill

Security audit

Chrome Relay

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently enables user-directed control of an attached local Chrome tab, including logged-in sessions, but it does not include hidden code or automatic unsafe behavior.

Install this only if you want the agent to control selected Chrome tabs, including pages where you are already signed in. Avoid attaching financial, admin, healthcare, or other sensitive tabs unless you explicitly want the agent to read and act on them, and detach the extension when finished.

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
  • 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
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This skill explicitly enables control of the user's real local Chrome profile and existing logged-in sessions, including reading page content, navigation, and arbitrary JavaScript execution in pages. Without a prominent user-facing warning in the skill description about access to authenticated sessions and page data, users may unknowingly authorize sensitive actions such as account interaction, data extraction, or transaction initiation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.