Back to skill

Security audit

创建公众号文章合集_无限

Security checks for vulnerabilities and agentic risk

Overview

The skill is a narrow browser workflow for creating a WeChat Official Account article collection, with some operational cautions but no evidence of hidden, destructive, or exfiltrating behavior.

Install only if you want an agent to operate an authenticated WeChat Official Account browser session and create a real article collection. Confirm the collection name and account context before invoking it, and prefer the documented OpenClaw browser profile rather than a personal browser profile.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill performs a live publishing action in the user's WeChat official account by clicking the final '发布' button, but it does not clearly require an explicit confirmation immediately before the irreversible account action. In an automation context, this can cause unintended content creation in a production account, especially if the user expected a draft-only workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The instructions repeatedly use URLs with lang=zh_CN, which indicates a forced locale choice in the skill behavior. The file does not offer the user a language/locale option or explain that the skill is intentionally limited to a China-region or Chinese-interface workflow.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

Earlier instructions require starting the browser with browser(action=start, target="host", profile="openclaw") and emphasize that openclaw is distinct from user (L052-L059). But L124 says the browser should first be started with browser(action=start, profile=user), which conflicts with the documented procedure and could cause the agent to use the wrong browser context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.