ClawHub
Back to skill

Security audit

Wechat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small public WeChat page summarization guide with clear limits against login, messaging, or private content access.

Install only if you want help summarizing public WeChat pages. Do not use it for private account actions, login-protected content, messaging, or anything requiring WeChat credentials.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is broad enough to match many generic requests related to WeChat, increasing the chance of unintended invocation. Mis-triggering can route unrelated user tasks into this skill's automation flow, causing unnecessary browsing of external pages, incorrect handling of user intent, or exposure to untrusted content without clear need.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.