ClawHub
Back to skill

Security audit

企业微信快速集成配置

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Enterprise WeChat setup guide whose sensitive behavior is expected for the integration, though users should secure credentials and govern customer-message automation.

Install only if you intend OpenClaw to interact with your Enterprise WeChat tenant. Use least-privilege WeCom apps, restrict visible departments and recipients, protect ~/.openclaw/config.yml from other users and source control, rotate exposed secrets, and test auto-replies in a limited group before using them with customers.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The guide instructs users to store live WeCom credentials directly in a local YAML config file, but provides no guidance on file permissions, secret rotation, or using a dedicated secret manager/environment variables. This increases the likelihood of credential leakage through backups, screenshots, shared home directories, or accidental source-control commits, which could allow unauthorized message sending or API access.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The customer-service automation section encourages monitoring and auto-replying to customer messages without any mention of user consent, data minimization, retention, or applicable privacy/compliance obligations. In a real enterprise setting, this can lead to unauthorized processing of customer communications and mishandling of personal or sensitive business data.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.