企业微信 AI Bot 对接

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Enterprise WeChat setup helper that stores a bot secret locally as part of its expected configuration flow.

Before installing, confirm you trust the referenced WeCom plugin source, protect your ~/.openclaw config files, avoid sharing or committing the Bot Secret, and consider using pairing or allowlist instead of the default open direct-message policy for production or sensitive workspaces.

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
91% confidence
Finding
The script persists the WeCom secret directly into a local JSON config file, and it does so without any warning, masking, permission hardening, or use of a dedicated secret store. If the config file has weak filesystem permissions, is backed up, synced, or exposed to other local users/processes, the credential can be recovered and used to impersonate or abuse the bot integration.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal