ClawHub
Back to skill

Security audit

睡后收入系统 V1（OpenClaw版）

Security checks across malware telemetry and agentic risk

Overview

The skill describes a coherent passive-income automation workflow, but it asks for recurring publishing, account credentials, and workspace-to-marketplace publishing without clear scope or approval controls.

Review carefully before installing. Only use it with explicit manual approval before WeChat draft upload or marketplace publication, restrict workspace scanning to an allowlisted folder, exclude credentials and private files, and store WeChat credentials only in approved secret storage.

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
95% confidence
Finding
The skill explicitly describes scanning the workspace, packaging accumulated experience, and publishing it to an external marketplace, but it provides no warning, consent gate, scope restriction, or guidance on excluding sensitive files. In an agent skill context, that creates a real risk of unintended exfiltration of secrets, internal documents, personal data, or proprietary content because users may not realize that broad workspace contents could be collected and shared externally.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.