Back to skill

Security audit

微信接龙解析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WeChat group-order parser that can create Tencent Docs spreadsheets, with privacy considerations but no evidence of deception or unsafe code.

Before installing, confirm you are comfortable with parsed group-order data being written to Tencent Docs when that connector is available. For sensitive groups, ask the agent to keep output local or remove room numbers before export.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

L173-L176 明确写明“唯一输出:按人接龙明细(透视表)”且“不需要商品汇总表”。但 L203-L232、L299-L305 又要求在解析完成后创建腾讯文档并写入两个 Sheet,其中 Sheet 2 明确是“商品订单汇总”。这属于文档内部对技能输出意图的直接矛盾。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to transmit parsed order data, including nicknames and possible room numbers, to Tencent Docs automatically when the connector is available, without requiring explicit user consent at the time of export. This creates a privacy and data-handling risk because potentially sensitive group chat content is sent to an external service and stored there, possibly exposing personal or household information beyond the user's immediate expectation.

Content

No source excerpt is available for this finding.