euthyna
About this skill
代码安全审计的判定纪律与交付门禁。当用户要求对一段代码、一个 PR、一次变更或一条已有的漏洞结论做安全审查与验证时使用。它做三件事：补上模型算不准的确定性事实（调用方、测试覆盖、git 历史来源），用 6 道门禁判定每条结论真假，拿不出证据的一律降级为「观察」而不是「发现」。不适用于：仅询问某个 CVE 的详情、仅要求跑一次现成扫描器、纯文档或格式化改动、以及用户只要一句快速摘要且明确接受风险时。
Security
This skill was reviewed and published through ClawHub's own moderation and security scanning pipeline before being listed on their registry. ClawHub checks for malicious code, dependency vulnerabilities, and policy violations.
When you run npx @agentpowers/cli install euthyna, AgentPowers downloads the package to a sandbox and runs a full security scan (ClamAV, Snyk, GuardDog, VirusTotal) before allowing installation. If the scan fails, installation is blocked.
Powered by ClawHub
This skill is sourced from ClawHub, a large open registry of community-built AI tools. By integrating ClawHub into AgentPowers, you get access to hundreds of additional skills while still benefiting from our security scanning, one-command install, and unified management through the AgentPowers CLI.
Getting started
New to AgentPowers? Learn how to install and use skills from the community.