ClawHub
Back to skill

Security audit

清除中文AI味

Security checks for vulnerabilities and agentic risk

Overview

This prompt-only skill rewrites Chinese text to sound less AI-generated and does not request system access or run code.

Install only if your intended use complies with school, workplace, publisher, or platform rules about AI-assisted writing. From a system-access perspective, this skill is low risk because it does not ask to run commands, access files, use credentials, connect to networks, or persist data.

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

Static analysis

No suspicious patterns detected.