Back to skill

Security audit

挑战杯小挑参赛助手-第十五届创业计划竞赛指南

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language contest preparation guide that provides advice and user-requested PPT workflow guidance without hidden execution, persistence, or data access.

Installers should understand this skill is intended for Chinese-speaking users preparing for the Challenge Cup competition. It may ask for project, team, business model, and contact details to prepare advice or slides, so users should avoid sharing sensitive information they do not want included in generated materials.

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
Findings (1)

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The entire skill file is written in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Static analysis

No suspicious patterns detected.