ClawHub
Back to skill

Security audit

翻译SKILL.md文档

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward translation helper that reads a user-chosen SKILL.md file and writes a Chinese translated copy, with its main overwrite risk disclosed.

Before using this skill, confirm the path is the intended skill directory and check whether SKILL(1).md already exists if you need to keep an earlier translation or manual edits.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly states it will overwrite an existing SKILL(1).md without warning. This can destroy prior translated content or user edits, creating an integrity and data-loss risk if the skill is invoked repeatedly or on the wrong directory.

Static analysis

No suspicious patterns detected.