Cloudflare 发布 security-audit 编码智能体技能
Cloudflare 发布了一个采用 MIT 许可证的编码智能体技能 security-audit,其仓库 README 经 GitHub Trending 曝光,称该技能可把编码智能体变成安全审计员。该技能以六个阶段运行——侦察、以覆盖率为导向的狩猎、候选验证、结构化输出、独立记录核验与目标中立报告,并采用隔离智能体与对抗式验证,确保核验者从不是发现者。发现结果写入符合 schema 的 JSON 文件,并由零依赖的 Node 校验器检查;Cloudflare 称该技能是其全舰队漏洞发现系统演化出的单仓库起点。安装通过 Skills CLI 完成,执行目标代码需要支持工具调用与并行子智能体的模型,以及操作系统级沙箱。
Cloudflare 称该技能是其多阶段、覆盖全舰队的漏洞发现系统的起点,为智能体驱动的安全审计提供了一个具体模板。
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
security-audit
A coding-agent skill that turns your agent into a security auditor. It orchestrates isolated agents through reconnaissance, coverage-led hunting, candidate validation, structured output, independent record verification, and target-neutral reporting.
This is the skill that seeded Cloudflare's vulnerability discovery harness, described in Build your own vulnerability harness. The harness grew into a multi-stage, fleet-wide system; this skill is the single-repo starting point it evolved from.
What it does
The skill runs a structured audit in six phases: