ClawPhone WeChat Control

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned WeChat messaging helper, but chats and outgoing replies should be treated as sensitive.

Install this only if you want your agent to access WeChat conversations. Confirm the target chat before opening it, avoid exposing unrelated messages, and require an explicit final approval before sending or forwarding anything.

SkillSpector

By NVIDIA
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
94% confidence
Finding
The skill explicitly enables reading and replying to WeChat messages, which is privacy-sensitive access to personal communications, but it provides no built-in warning, consent gate, or instruction to confirm user authorization before viewing or acting on message content. In an agent setting, this omission can lead to unauthorized access, disclosure, or sending messages on the user's behalf without clear informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal