Back to skill

Security audit

产学研资源对接助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static Chinese-language guidance/template resource for industry-academia collaboration and startup incubation, with no evidence of hidden execution, persistence, credential use, or data exfiltration.

Installers should treat this as general business and commercialization guidance, not verified legal, investment, or contact data. Verify current investor, incubator, policy, and contract information before acting on it.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

声明描述的是一个具备实际业务能力的资源对接与创业孵化助手,但代码中只有一个示例/占位脚本,唯一行为是打印“This is an example script for industry-academia-connector”。不存在与声明相符的核心逻辑、数据处理、API 调用、检索、匹配或工作流实现。因此代码实际行为与声明用途存在明显且实质性的偏差,应判定为不匹配。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad business terms such as '企业合作', '投资机构', and '产业资源', which can cause the skill to activate for generic requests outside its precise scope. Over-broad activation increases the chance of inappropriate routing, unnecessary exposure of business-planning advice, and user confusion, though it is not a direct code-execution or data-exfiltration issue.

Content

No source excerpt is available for this finding.