ClawHub
Back to skill

Security audit

心理学研究设计助手

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language psychology research design assistant with no executable code, credential use, persistence, or hidden data access.

Install this if you want a Chinese-language assistant for psychology research design. Users should still verify real citations, scales, ethics requirements, and current regulations independently, especially because the skill explicitly avoids replacing literature search or institutional ethics review.

SkillSpector

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

Medium
Confidence
93% confidence
Finding
The template is entirely written in Chinese and structures the output in that language without any indication that the user's language preference was checked or that multilingual output is optional. This can override or disregard user choice, causing usability and accessibility issues, and in some settings may lead reviewers to miss important safety or methodological details if they are not fluent in Chinese.

Static analysis

No suspicious patterns detected.