ClawHub
Back to skill

Security audit

师生共创模式指导-高校科技成果转化方法论

Security checks for vulnerabilities and agentic risk

Overview

This is a content-only Chinese guidance skill for university teacher-student startup collaboration, with no harmful execution, persistence, credential use, or hidden data access found.

Install only if you are comfortable using a Chinese-language advisory skill about university technology commercialization. Treat its equity, governance, IP, and commercialization suggestions as educational guidance and verify important decisions with qualified legal, university, or business advisors.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The declared description presents a substantive assistant for advising on university teacher-student co-creation workflows. However, the actual code chunk does not implement any such functionality. It is a generic placeholder script whose only behavior is printing a static example message. This is a material mismatch in primary purpose and actual capability: the description claims a domain-specific guidance skill, while the code provides no meaningful related behavior.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The manifest description and the full skill content are written entirely in Chinese, and the file does not state that the skill is China-specific or offer users an option to interact in another language. This can violate language or locale policy when users are not given an explicit opt-in for a forced language experience.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
SQP-3 applies to all file types and flags language or locale policy violations in natural-language content. This markdown file presents all instructions and guidance only in Chinese, with no indication that the user can opt into another language or that the Chinese-only scope is justified as region-specific.

Static analysis

No suspicious patterns detected.