Back to skill

Security audit

xinjianxue-skill-mentor-cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed paid HTTP API integration that asks for consent before sending personal profile details for a mentor-guidance report.

Before installing, be comfortable sharing the requested personal details with the service domain and understand that use consumes account credits. Provide the one-time authorization code only when you intentionally want to bind this AI to your account, and keep the resulting credentials in a proper secret store.

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