medusa
installs/mo · pypistarsforks
How to install medusa?
pantheon-security/medusa
$git clone https://github.com/Pantheon-Security/medusaAI-first security scanner with 40,000+ detection patterns for AI/ML, agents, and LLM applications. 🤖 Works out of the box - no tool installation required. 🚨 200 CVEs: Log4Shell, Spring4Shell, XZ Utils, LangChain RCE, MCP-Remote RCE, React2Shell **🔥 `medusa scan --g
README.md
| 1 | # 🐍 MEDUSA - AI Security Scanner |
| 2 | |
| 3 | [](https://pypi.org/project/medusa-security/) |
| 4 | [](https://pypi.org/project/medusa-security/) |
| 5 | [](https://www.python.org/downloads/) |
| 6 | [](https://www.gnu.org/licenses/agpl-3.0) |
| 7 | [](https://github.com/Pantheon-Security/medusa/actions/workflows/test.yml) |
| 8 | [](https://github.com/Pantheon-Security/medusa) |
| 9 | [](https://github.com/Pantheon-Security/medusa) |
| 10 | [](https://github.com/Pantheon-Security/medusa) |
| 11 | |
| 12 | **AI-first security scanner with 40,000+ detection patterns for AI/ML, agents, and LLM applications.** |
| 13 | **🤖 Works out of the box - no tool installation required.** |
| 14 | **🚨 200 CVEs: Log4Shell, Spring4Shell, XZ Utils, LangChain RCE, MCP-Remote RCE, React2Shell** |
| 15 | **🔥 `medusa scan --git <URL>` — Scan any repo for AI supply chain attacks (repo poisoning, prompt injection, MCP tool poisoning)** |
| 16 | **🔐 `medusa secrets scan` — Find leaked API keys in your Claude / Cursor / Copilot / shell history. 21 issuer types. Interactive in-place redaction.** |
| 17 | **🚀 v2026.7.0: Claude Code compromise detection, an always-on AI attack-signature scanner, native Rust & PHP security rules, and rule-level diagnostics — on top of 40,000+ detection patterns.** |
| 18 | |
| 19 | --- |
| 20 | |
| 21 | ## 🎯 What is MEDUSA? |
| 22 | |
| 23 | MEDUSA is an AI-first security scanner with **40,000+ detection patterns** that works out of the box. Simply install and scan - no external tool installation required. MEDUSA's built-in rules detect vulnerabilities in AI/ML applications, LLM agents, MCP servers, RAG pipelines, and traditional code. |
| 24 | |
| 25 | ### ✨ Key Features |
| 26 | |
| 27 | - 🔥 **`medusa scan --git <URL>`** - Scan any GitHub repo for AI supply chain attacks in seconds |
| 28 | - 🔐 **`medusa secrets scan` + `purge`** - Find API keys / tokens / private keys leaked into Claude Code / Cursor / Copilot / Zed / Gemini chat histories *and* your bash / zsh / psql / mysql / python REPL history. 21 issuer types (Anthropic, OpenAI, PyPI, GitHub PATs, AWS, GCP, Stripe, Slack…). Interactive `[y/n/s/a/q]` purge with mandatory byte-identical backup and JSONL-safe redaction. Local-only, no telemetry. |
| 29 | - 🤖 **40,000+ AI Security Patterns** - Industry-leading coverage for AI/ML, agents, and LLM applications |
| 30 | - 🛡️ **Repo Poisoning Detection** - Detects weaponized AI editor configs across 28+ file types (Cursor, Cline, Copilot, Claude Code, Gemini, Kiro, and more) |
| 31 | - 🚀 **Zero Setup Required** - Works immediately after `pip install` - no tool installation needed |
| 32 | - 🚨 **200 CVE Detections** - Log4Shell, Spring4Shell, XZ Utils backdoor, LangChain RCE, MCP remote code execution, React2Shell, and more |
| 33 | - ⚡ **Parallel Processing** - Multi-core scanning (10-40x faster than sequential), works on macOS/Windows/Linux |
| 34 | - 🎨 **Beautiful CLI** - Rich terminal output with progress bars |
| 35 | - 🧠 **IDE Integration** - Claude Code, Cursor, VS Code, Gemini CLI support |
| 36 | - 🔄 **Smart Caching** - Skip unchanged files for lightning-fast rescans (content-hash keyed, correct in CI) |
| 37 | - ⚙️ **Configurable** - `.medusa.yml` for project-specific settings |
| 38 | - 🌍 **Cross-Platform** - Native Windows, macOS, and Linux support |
| 39 | - 📊 **Multiple Reports** - JSON, HTML, Markdown, SARIF exports for any workflow |
| 40 | - 🔧 **Optional Linter Support** - Auto-detects external linters if installed for enhanced coverage |
| 41 | |
| 42 | ### 🆕 What's New in v2026.7.0 |
| 43 | |
| 44 | **Claude Code supply-chain detection, broader language coverage, and rule-level observability.** |
| 45 | |
| 46 | | | Change | Details | |
| 47 | |---|---|---| |
| 48 | | 🛡️ | **Claude Code compromise d |
People who liked this also viewed
6 picksType
- mcp-scannerScan MCP servers for potential threats & security findings.MCP ServersJul 2026
- hol-guardOpen-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.MCP ServersJul 2026
- agent-scanSecurity scanner for AI agents, MCP servers and agent skills.MCP ServersJul 2026
- falcon-mcpConnect AI agents to CrowdStrike Falcon for automated security analysis and threat huntingMCP ServersJul 2026
- python🔐 Plug-and-play auth for Python MCP servers.MCP ServersAug 2025
- auth0-mcp-serverConnect LLMs and AI agents to Auth0 Management APIs via an MCP server. Use natural-language commands to create apps, deploy Actions, and query logs—runs locally and supports interactive tenant authentication for secure Auth0 administration from AI tools/CLIs.MCP ServersJul 2026
