.cursor/skills/codo-audit/SKILL.md
Runs a phased code security audit: recon, vulnerability scanning by type, second-round verification, and final report. Use when the user asks for 安全审计、漏洞扫描、code audit、security review, or wants to find SQL/RCE/SSRF/auth/file/logic vulnerabilities in the codebase.
npx skillsauth add yux1azhengye/codo-audit-skill-for-cursor-demo codo-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
按五阶段执行:参数与范围 → Recon → 专项扫描 → 二轮验证与误报过滤 → 攻击链与报告。规则与产出物格式写死在本文及引用文件中,便于复现。
./audit-report/,可指定。<报告目录>/audit-report.md。<报告目录>/recon.json(或等价结构);Round 1 原始发现 <报告目录>/round1-findings.md;二轮确认后 <报告目录>/confirmed-findings.md。以下类型不进入终报,二轮前即可规则过滤:
先规则排除,再对剩余项做 AI 复核(见 prompts/false-positive-rules.md)。
pom.xml/build.gradle → Java;go.mod → Go;requirements.txt/setup.py → Python;composer.json → PHP;*.csproj/*.sln → ASP/ASP.NET;package.json → Node.js)。<报告目录>/recon.json 或等价):
user_id、role、is_admin、skip_auth 等语义,枚举相关路由并在 Service 层追踪用法。<报告目录>/round1-findings.md,每条暂不要求终报格式,但需包含 Source、Sink、简要描述。round1-findings.md 应用误报规则,剔除不进入终报的类别(见上文误报控制)。<报告目录>/confirmed-findings.md。confirmed-findings.md 做产出物×攻击面关联,见 prompts/attack-chain.md。<报告目录>/audit-report.md。| 阶段 | 产出物 | 下一步 | |------------|-------------------------|------------------| | Step 0 | 参数摘要 | Recon | | Step 1 | recon.json | Round 1 选 Sink | | Step 2 | round1-findings.md | 二轮验证 | | Step 3 | confirmed-findings.md | 攻击链与报告 | | Step 4 | audit-report.md | 结束 |
所有规则、产出物路径与格式均固定,便于在其他载体上复现同一套审计流程。
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.