跳到正文
cccskills
免费在 GitHub 公开

shannon

Autonomous AI security pen testing. Executes real exploits against web applications to find SQL injection, XSS, SSRF, authentication flaws, and IDOR vulnerabilities. Reports only confirmed, reproducible findings — no false positives.

中文简介正在准备中。当前显示原文说明。

集成工具Docker

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md4.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Shannon — Autonomous AI Pentester

Shannon is a white-box security testing framework that analyses source code, maps attack surfaces, and executes real attacks. Use it against development and staging environments before deploying to production.

IMPORTANT — Authorization Gate: Shannon executes real attacks. You must have explicit written authorisation to test the target system. Shannon confirms this before every run. Never target production systems or systems you do not own.

Install

npx skills add unicodeveloper/shannon

Prerequisites: Docker (all attack tools run in containers) and an Anthropic API key.

Usage

# Full pentest of a local app
/shannon http://localhost:3000 myapp

# Target specific vulnerability categories
/shannon --scope=xss,injection http://localhost:8080 frontend

# Named workspace (allows resuming if interrupted)
/shannon --workspace=audit-q1 http://staging.example.com backend-api

# Check status of a running pentest
/shannon status

# View the latest report
/shannon results

What Shannon Tests

Shannon covers 50+ specific vulnerability types across 5 OWASP categories:

Injection

  • SQL injection (union-based, blind, time-based)
  • Command injection
  • Server-Side Template Injection (SSTI)
  • NoSQL injection

Cross-Site Scripting (XSS)

  • Reflected XSS
  • Stored XSS
  • DOM-based XSS
  • XSS via file upload
  • Mutation XSS

SSRF

  • Internal service access
  • Cloud metadata endpoints (AWS IMDSv1/v2, GCP, Azure)
  • DNS rebinding
  • Protocol smuggling

Broken Authentication

  • Default / weak credentials
  • JWT algorithm confusion (none algorithm, weak signing)
  • Session fixation
  • CSRF
  • MFA bypass patterns

Broken Authorisation

  • Insecure Direct Object References (IDOR)
  • Privilege escalation
  • Path traversal
  • Forced browsing
  • Mass assignment

5-Phase Pipeline

Shannon runs these phases automatically, in parallel where safe:

PhaseWhat happens
Pre-ReconStatic source code analysis + external scans (Nmap, Subfinder, WhatWeb)
ReconLive attack surface mapping via headless browser
Vulnerability Analysis5 parallel specialist agents (injection, XSS, SSRF, auth, authorisation)
ExploitationEach agent spawns a dedicated exploit agent; real attacks executed
ReportingExecutive summary + reproducible PoC for every confirmed finding

Runtime and Cost

  • Full pentest: ~1–1.5 hours
  • Cost: ~$50 using Claude Sonnet (varies with app complexity)
  • Benchmark: 96.15% exploit success rate on the XBOW security benchmark (100/104 exploits)

Scope Controls

# Limit to specific vulnerability categories
/shannon --scope=xss,injection http://localhost:3000 app

# Exclude sensitive paths
/shannon --avoid=/logout,/admin/delete http://localhost:3000 app

# Test only authenticated endpoints (provide session cookie)
/shannon --cookie="session=abc123" http://localhost:3000 app

Safety Gates Built In

  • Authorisation confirmation at every invocation — Shannon will not proceed without explicit confirmation
  • Production warning — warns loudly if the target looks like a production URL
  • Docker isolation — all attack tools run inside containers; nothing executes on your host
  • Scope controls — use --avoid to protect specific paths (e.g., /logout, data-deletion endpoints)

Reading the Report

Shannon's report includes only confirmed exploits — if it can't prove a vulnerability, it doesn't report it.

Each finding includes:

  • Vulnerability type and OWASP category
  • Severity (Critical / High / Medium / Low)
  • Affected endpoint and parameter
  • Reproducible proof-of-concept (PoC) steps
  • Recommended remediation

Tips

  • Run Shannon against every staging deployment before merging to main
  • Focus first on the API layer (/api/*) — most exploitable surface for web apps
  • Use --workspace to name runs so you can compare results across deployments
  • Fix Critical and High findings before shipping; schedule Medium/Low for the next sprint
  • Re-run Shannon after fixing findings to confirm remediation is effective

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

中文简介正在准备中。当前显示原文说明。

nvdigitalsolutions/mcp-ai-wpoos72026年10月23日 更新

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

中文简介正在准备中。当前显示原文说明。

nvdigitalsolutions/mcp-ai-wpoos72026年10月23日 更新

Control a headless browser to navigate URLs, click elements, fill forms, extract content from JavaScript-rendered pages, take screenshots, and automate end-to-end web workflows.

中文简介正在准备中。当前显示原文说明。

nvdigitalsolutions/mcp-ai-wpoos72026年10月23日 更新

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

中文简介正在准备中。当前显示原文说明。

nvdigitalsolutions/mcp-ai-wpoos72026年10月23日 更新

Review code for quality, simplicity, and maintainability. Identifies unnecessary abstractions, duplicated logic, oversized functions, missing error handling, and naming issues — then fixes them automatically before presenting the result.

中文简介正在准备中。当前显示原文说明。

nvdigitalsolutions/mcp-ai-wpoos72026年10月23日 更新

WooCommerce store operations through NV oOS Pro — product research, catalog cross-referencing, inventory lookups, and Shopify or Flowhub comparisons where integrations are configured.

中文简介正在准备中。当前显示原文说明。

nvdigitalsolutions/mcp-ai-wpoos72026年10月23日 更新

查看 nvdigitalsolutions 的全部技能

报告此技能的问题