ClawHub
Back to skill

Security audit

ClawPhone WeChat Control

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WeChat automation helper, but users should remember it can read and send private chat messages when invoked.

Install only if you are comfortable letting the agent view the active WeChat screen and act in chats you request. Confirm the target contact/thread and message content yourself before asking it to send, especially when unrelated chats may be visible.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly supports reading and replying to WeChat messages, which involves access to highly privacy-sensitive personal communications, but it provides no user-facing warning, consent boundary, or guidance on limiting access to only the requested content. In an agentic/mobile-control context, this increases the risk of over-collection, accidental exposure of unrelated messages, and actions taken on behalf of the user without clear privacy disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.