ClawHub
Back to skill

Security audit

WeChat Content Creator

Security checks for vulnerabilities and agentic risk

Overview

This is a content-writing guide for WeChat public-account articles, with no executable code, credential access, hidden data flow, or persistence.

Install this if you want an agent to draft and optimize WeChat public-account content, especially Chinese-language commercial articles. Review facts carefully for legal or finance topics, and do not allow any connected publishing tool to upload or post drafts without your explicit approval.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises very broad trigger phrases such as general article writing, title optimization, topic selection, and keyword optimization, which can cause the agent to invoke this skill for ordinary writing requests that do not specifically require WeChat-public-account constraints. That can override user intent, force niche-specific behavior, or steer outputs toward monetization and platform-specific formatting in contexts where it is inappropriate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill strongly constrains output structure and examples to Chinese-language WeChat content without giving the user a language choice or declaring a justified locale boundary. If auto-invoked for multilingual or non-Chinese requests, it can produce the wrong language or culturally mismatched output, reducing reliability and potentially causing inappropriate task routing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.