warden-audit
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "warden-audit":https://skillpi.com/zh/skills/deepskill-c25670fae9ee7615083bee4b9d8c7b3b004288e8174bffb19b514520577d191b。安装前核对上游来源和版本:https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/warden-audit/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/warden-audit --skill warden-audit来源与配置
查看 GitHub 源码jeremylongshore/tons-of-skills-marketplace固定提交 6ea46b08dce892944db7c16f28d0b5308d402402
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目收录公开技能“warden-audit”,按来源分类归入「测试与安全校验」使用场景、「软件开发与 IT」职业。目录标签:ai-lab、安全审计、漏洞扫描、密钥检测。此页用于按主题发现相关资源;请通过固定原站版本核对实际能力、依赖环境和所需权限。本站仅提供独立目录介绍与原站入口,原始文件和附件依各自许可开放。
文件浏览
--- name: warden-audit description: Full security audit — secrets, dependencies, IAM, auth, injection, XSS, HTTPS, rate limiting, public storage. Use when asked for "security audit", "check for vulnerabilities", "security review", or "are we secure". allowed-tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion version: 0.6.4 author: tonone-ai <hello@tonone.ai> license: MIT --- # Full Security Audit You are Warden — the security engineer on the Engineering Team. ## Steps ### Step 0: Detect Environment Identify the project's stack and security posture: - Check for frameworks: `package.json`, `requirements.txt`, `go.mod`, `Cargo.toml`, `Gemfile` - Check for cloud platform: GCP, AWS, Azure configs (`gcloud`, `aws`, Terraform, Pulumi files) - Check for auth: middleware, JWT configs, session management, OAuth setup - Check for CI/CD: `.github/workflows/`, `Dockerfile`, `cloudbuild.yaml` - Check for dependency lock files: `package-lock.json`, `yarn.lock`, `poetry.lock`, `Pipfile.lock`, `go.sum` If the stack is ambiguous, ask the user. ### Step 1: Scan for Hardcoded Secrets Search the codebase for exposed secrets: - API keys, tokens, passwords in source files (not just `.env`) - Patterns: `sk-`, `AKIA`, `ghp_`, `Bearer `, base64-encoded credentials - Check `.env` files committed to git (should be in `.gitignore`) - Check CI/CD configs for inline secrets - Check for private keys (`.pem`, `.key` files) ### Step 2: Scan Dependencies Check for vulnerable dependencies: - Read lock files and check for known CVEs - Look for outdated major versions with known security issues - Check for typosquatting risks (similar package names) - Verify dependency sources (no private registries without auth) ### Step 3: Check IAM and Access Control Review access control configuration: - IAM roles and policies — any wildcards or overly permissive? - Service accounts — shared across services? Over-privileged? - API keys — rotated? Scoped? Rate-limited? - Admin access — who has it? Is it justified? ### Step 4: Check Application Security Review application code for common vulnerabilities: - **Auth on endpoints** — are all sensitive endpoints protected? - **SQL injection** — raw SQL with string interpolation? - **XSS** — unescaped user input rendered in HTML? - **CSRF** — forms without CSRF tokens? - **HTTPS** — is TLS enforced? Any HTTP fallbacks? - **Rate limiting** — present on auth endpoints and public APIs? - **Security headers** — HSTS, CSP, X-Frame-Options, X-Content-Type-Options? - **CORS** — overly permissive? Allows all origins? - **Public storage** — S3 buckets, GCS buckets, or blobs publicly accessible? ### Step 5: Report by Severity Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose. ``` ## Security Audit Report ### Critical - [issue] — [location] — [fix] ### Warning - [issue] — [location] — [fix] ### Info - [observation] — [recommendation] ### Summary | Category | Status | |---|---| | Secrets | [status] | | Dependencies | [status] | | IAM | [status] | | Auth | [status] | | Injection | [status] | | Headers | [status] | | Rate Limiting | [status] | | Storage | [status] | ``` Use severity indicators: Critical for actively exploitable issues, Warning for weaknesses that increase risk, Info for best-practice improvements. ## Delivery If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
当前收录版本
0.6.4
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
提供全面安全审计能力,覆盖密钥、依赖项、IAM、身份验证、注入攻击、XSS、HTTPS、速率限制、公开存储等关键安全维度
评分依据
触发词精准完整,覆盖多种变体,边界清晰
评分依据
Phase/步骤清晰(Step 0-5),有出口条件,含端到端示例
评分依据
工具来源明确,参数正确,覆盖主要异常
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
-
账号、密钥或授权
使用专用、最小权限账号,不把密钥粘贴到公开内容或命令日志;核对接收数据的服务与租户。
主文档提及 · 第 22, 33 行
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。