ClawHub
Back to skill

Security audit

WeCom Connect

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a clearly described WeCom/OpenClaw connection flow, with sensitive local credential storage and gateway restart that are expected for the integration.

Install this if you intend to connect Enterprise WeChat to OpenClaw. Be aware that after you authorize WeCom, the agent will store the returned bot secret in ~/.openclaw/openclaw.json, enable the WeCom channel, and restart the OpenClaw gateway; review local config permissions and ask the agent to show the intended config change first if you want an extra confirmation step.

A.I.G

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

SkillSpector

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill directs the agent to persist newly obtained bot credentials into a local configuration file and restart the gateway, but it does not require explicit user confirmation immediately before making those system changes. Modifying local config and restarting a service can change runtime behavior, affect availability, and store sensitive secrets on disk without clear disclosure, which is unsafe even if the intended function is legitimate integration setup.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.