Back to skill

Security audit

mmxagent-skill-wecom

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a coherent WeCom connection setup for OpenClaw, with credential storage and gateway restart that are expected for that purpose but worth understanding before use.

Install only if you intend this skill to connect OpenClaw to WeCom. Expect it to contact work.weixin.qq.com, store the returned bot secret in ~/.openclaw/openclaw.json, enable the WeCom channel, and restart the OpenClaw gateway after you confirm authorization is complete. Keep that config file protected because it will contain a bot secret.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to obtain a bot secret, write it into a local configuration file, enable the channel, and restart the gateway without any explicit consent, secret-handling guidance, or validation of secure file permissions. This can expose sensitive credentials to unintended access, silently alter local runtime behavior, and create persistence for a newly connected external integration.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest describes a workflow for obtaining an authorization link, completing WeCom authorization, and binding a WeCom robot. Restarting the local gateway is a broader system-management action outside that narrowly stated connection flow, and the documentation does not justify why a service restart is within scope.

Content

No source excerpt is available for this finding.