Back to skill

Security audit

Wechat pay tutorial

Security checks for vulnerabilities and agentic risk

Overview

This is a WeChat Pay guidance skill with no executable code; users should only be aware that some payment-limit advice is China/RMB-specific and may vary by region.

Before installing, understand that this skill is informational and China-market-oriented. For real payment decisions, merchant integrations, password-free limits, refunds, and cross-border support, confirm the user's region and current WeChat Pay documentation or in-app settings.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill references locale-specific payment behavior using 'under 1000 RMB' as a default operational rule, and the document broadly presents itself as a general specialist guide rather than explicitly scoping itself to China or offering locale choice. This can create a natural-language locale policy issue because the skill implicitly forces a region-specific frame without documenting that limitation.

Content

No source excerpt is available for this finding.