ClawHub
Back to skill

Security audit

Wechat Work

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple public Enterprise WeChat page summarizer with clear limits against private or internal access.

Use this only for public Enterprise WeChat share, announcement, app, or invitation pages. Do not rely on it for private chats, tenant data, admin actions, authenticated enterprise workflows, or anything requiring internal permissions.

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
88% confidence
Finding

The activation description is overly broad: '当需要访问或自动化企业微信相关内容时调用' could match many generic Enterprise WeChat requests, causing the agent to invoke this skill in contexts beyond its stated safe boundary of only public pages. That mismatch increases the chance of over-selection, unintended browsing, or handling requests that imply internal enterprise data or automation workflows the skill should not perform.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.