Back to skill

Security audit

xinjianxue-skill-long_distance-cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed paid API integration for long-distance relationship analysis, with user consent and credential handling instructions.

Before installing, understand that using this skill means sharing personal birth/location details with the Xinjianxue API and letting the agent store an API credential in a secret store for future calls. Only provide the one-time authorization code when you intend to bind this AI to your Xinjianxue account and spend service credits.

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