Back to skill

Security audit

企业微信快速集成配置

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent WeCom integration guide, but it asks users to configure powerful messaging credentials and customer-message automation without enough security or privacy safeguards.

Install only if you are authorized to connect OpenClaw to your organization's WeCom tenant. Treat app secrets, access tokens, and webhook URLs as credentials: restrict config file permissions, do not commit or share them, redact them from logs and screenshots, and rotate them if exposed. Confirm your organization permits automated monitoring and replies for customer messages before enabling that workflow.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:43
Finding

Plaintext Storage of WeCom Application Secrets and Webhook Credentials

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs users to place sensitive WeCom credentials such as CorpId, AgentId, and especially the application Secret directly into a local plaintext config file, but provides no warning about secure storage, file permissions, redaction, or accidental disclosure through backups and logs. In an integration skill, this context makes the issue more dangerous because these credentials enable message sending and API access if the host or config is exposed.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill promotes automatic monitoring and replying to customer WeCom messages without any discussion of privacy, consent, data retention, or organizational policy controls. Because this involves customer communications, the omission can lead to unauthorized processing of personal or sensitive business data and noncompliant automation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The configuration examples include group bot webhook URLs without warning that the webhook key embedded in the URL is effectively a bearer secret. If copied into tickets, repos, chat, or screenshots, an attacker could abuse the webhook to send spoofed messages into enterprise group chats.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 172)May include surrounding context.

  1. 确认机器人未被删除
  2. 测试 URL 可达性:
    bash
    curl -X POST "YOUR_WEBHOOK_URL" \
      -H "Content-Type: application/json" \
      -d '{"msgtype":"text","text":{"content":"测试"}}'
    

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description and the rest of the skill content are presented only in Chinese, and the author metadata frames it as a Chinese ecosystem skill. Under the policy rule, forcing a specific language without user choice can be a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description and keywords indicate the skill is targeted specifically at Chinese/WeCom usage (e.g. Chinese description text and the keyword "chinese"), but the file does not state that this locale restriction is optional or justified as a region-specific tool. Under the policy rule, forcing or implying a specific language/locale without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.