YottaMeta

Yotta Security Audit — Security skill for Claude Code

Security community

元安是一个零依赖的跨智能体安全扫描引擎.

How to install Yotta Security Audit

This entry records only its repository, not the path inside it, so there is no exact command to give. Open YottaMeta/yotta-security-audit and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Yotta Security Audit does

元安是一个零依赖的跨智能体安全扫描引擎。它内置 13 类规则，专门检测 AI 技能中的恶意模式——供应链投毒、提示注入、危险命令、越权访问等，并提供 Windows / Linux 双平台系统安全基线检查（纯只读，绝不执行修复）。它能自动发现技能目录，生成文本 / JSON / Markdown 三种报告（默认脱敏）。它只检测与报告，绝不擅自删除、修复或查杀——让「把第三方技能装进任何智能体」这件事，变成一道可审计的安检门。

Alternatives in Security

Pal — Multi-model AI integration — chat, debugging, code review, planning, security audit 11.3k ★
Skills — Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows 4k ★
/web3 Audit — Smart contract security audit using the 10-bug-class methodology 927 ★

README

Language: English · 中文

yotta-security-audit · 元安 (Yuan'an)

YottaMeta's AI-skill supply-chain & system security scan engine: detects malicious skill patterns · scans system security baselines, purely read-only, zero-dependency and disciplined. Use it before installing a new skill, for periodic audits of installed skills, or to check system security baselines — wherever correctness and safety matter.

Activates when the user mentions security audit / skill security check / malicious detection / supply-chain security / system security baseline / scan skills / supply chain / malicious skill, or asks to scan a skill; running it before installing any new skill is recommended — judged by the target, not keyword luck.

Python 3.8+ standard library, zero external dependencies; Windows + Linux; read-only detection, reports masked by default, with authorization & legal boundaries declared.