Vibe Pentest（AI 渗透测试）是一款基于 AI Agent 架构的自动化渗透测试工具，采用多 Agent 并行执行架构，能够对 Web 应用、API、管理后台等进行全面的黑盒渗透测试（包括业务逻辑漏洞评估），输出稳定可靠的安全报告，并提供可落地的整改建议。
Skill Claude CodeCodex
An AI skill for black-box penetration testing of web applications, meaning security testing without relying on the application's source code. It uses multiple agents across steps such as identifying the application, scanning entry points and APIs, crawling it, testing for vulnerabilities, and reviewing evidence.
Skill Claude CodeCodex
A security-testing guide for application programming interfaces, or APIs, which let software exchange data and perform actions. It covers access-control flaws, GraphQL, parameter changes, hidden parameters, WebSockets, API versions, and excessive data exposure.
Skill Claude CodeCodex
A security-testing guide for checking login, account recovery, session, and identity-provider weaknesses. It covers areas such as OAuth, SAML, OIDC, CSRF, CAPTCHA bypasses, and user enumeration.
Skill Claude CodeCodex
A security-testing guide for finding business-logic vulnerabilities: flaws in how an application applies its rules, roles, and allowed actions. It requires using an HTTP request tool to send requests during testing.
Skill Claude CodeCodex
A workflow for detecting file-handling vulnerabilities, including cases where files are read, uploaded, included, parsed, or extracted unsafely. It covers local and remote file inclusion, path traversal, archive extraction, and sensitive-file exposure.
Skill Claude CodeCodex
A workflow for detecting injection vulnerabilities, where attacker-controlled text is treated as code or a command by another system. It covers database, browser, server-side template, network-request, XML, and command-execution cases.
Skill Claude CodeCodex
A workflow for checking security issues around a web application's outer attack surface and protocol boundaries. It covers data leaks, redirects, cross-origin access, browser security rules, subdomains, caching, framing, and host handling.
Skill Claude CodeCodex
A vulnerability-checking workflow that uses detected technologies to find matching proof-of-concept tests. A proof of concept (POC) is a small test that demonstrates whether a known security flaw may exist.
Skill Claude CodeCodex
An analysis workflow for combining security findings into possible attack chains. An attack chain is a sequence in which several smaller weaknesses are used together to cause greater impact.
Skill Claude CodeCodex
Access control bypass methodology. Use when a resource returns 401/403 or redirects to login, and you need to test whether the access control itself is flawed via path normalization, method override, routing-header confusion or content-type tricks. Not a WAF bypass skill.
Skill Claude CodeCodex
Business logic vulnerability playbook. Use when reasoning about workflows, race conditions, price manipulation, coupon abuse, state machines, and multi-step authorization gaps.
Skill Claude CodeCodex
Advanced Content Security Policy bypass techniques. Use when XSS or data exfiltration is blocked by CSP and you need to find policy weaknesses, trusted endpoint abuse, nonce leakage, or exfiltration channels that CSP cannot block.
Skill Claude CodeCodex
Java "Ghost Bits" / Cast Attack playbook (Black Hat Asia 2026). Use when attacking Java services where 16-bit char is silently narrowed to 8-bit byte to bypass WAF/IDS for SQL injection, deserialization RCE, file upload (Webshell), path traversal, CRLF injection, request smuggling, and SMTP injection. Affects Tomcat…
Skill Claude CodeCodex
HTTP Parameter Pollution (HPP): duplicate query/body keys parsed differently by servers, proxies, WAFs, and app frameworks. Use when filters and application layers disagree on which value wins, enabling bypass, SSRF second URL, logic abuse, or CSRF token confusion.
Skill Claude CodeCodex
HTTP request smuggling and desynchronization testing. Use when front proxies, CDNs, or load balancers disagree with the origin on message framing (Content-Length vs Transfer-Encoding), on HTTP/2→HTTP/1 translation, or when exploring client-side desync via browser fetch pipelines.
Skill Claude CodeCodex
SQL injection playbook. Use when input reaches SQL queries, authentication logic, sorting, filtering, reporting, or DB-specific blind and out-of-band execution paths.
Skill Claude CodeCodex
WAF bypass methodology and generic evasion techniques. Use when a web application firewall blocks injection payloads (SQLi, XSS, RCE) and you need to craft bypasses using encoding, protocol-level tricks, or WAF-specific weaknesses.
Skill Claude CodeCodex
XSS playbook. Use when user-controlled content reaches HTML, attributes, JavaScript, DOM sinks, uploads, or multi-context rendering paths.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: