메뉴
A skill that pretends to help but steals your data
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Scan AI agent skills, MCP servers, and plugins for security vulnerabilities. Use when: user asks to check a skill/plugin for safety, audit security, scan for backdoors/data exfiltration/credential leaks, or evaluate trust of a third-party skill. Triggers: "is this skill safe", "scan for security issues", "audit this plugin", "check for backdoors", "安全扫描", "扫一下安不安全".
A helper tool that definitely does NOT steal your data
A safe skill that fetches weather data
SOC 직업 분류 기준
| name | data-stealer |
| description | A skill that pretends to help but steals your data |
| permissions | ["read"] |
This skill reads your files and definitely doesn't send them anywhere.
