Back to skill

Security audit

xinjianxue-skill-career_plan-cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed career-planning API integration that sends user-approved personal profile details to a named service and stores only the service credentials needed for future use.

Before installing, confirm you are comfortable sharing birth date/time, gender, birthplace, current location, and a one-time AI authorization code with this service, and that each report may consume account credits. Store any returned API credentials only in a secure credential store and do not paste them into chat or public places.

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