Back to skill

Security audit

小游戏5分钟报告

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward report generator that openly uses a Tencent WeChat games page and Feishu delivery, with no hidden code or persistence found.

Before installing, make sure your environment allows scraping the Tencent page and sending generated reports through Feishu. Use a Feishu account and recipient list appropriate for this business-intelligence workflow, and review the report before delivery if the content could affect investment or competitive decisions.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly performs external web scraping and then sends the generated output via Feishu direct message, but it does not warn the user that third-party data will be collected and transmitted through another platform. This creates a transparency and consent gap that can lead to unintended data transfer, policy violations, or misuse in environments where outbound messaging and scraping require explicit user approval.

Content

No source excerpt is available for this finding.