No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Pantheon-Security · MCP Server · ★ 962
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is medusa safe to install? View the security audit →
🐍 MEDUSA - AI Security Scanner AI-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 🔥 — Scan any repo for AI supply chain attacks (repo poisoning, prompt injection, MCP tool poisoning) 🔐 — Find leaked API keys in your Claude / Cursor / Copilot / shell
| Stars | 962 |
| Forks | 153 |
| Language | Python |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 68.0746868959104/100 |
| Open Issues | 2 |
| Last Updated | 2026-08-10 |
| Created | 2025-11-15 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~22k |
Looking for a medusa alternative? If you're comparing medusa with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mappe
IAM for your AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, revi
A security scanner for your LLM agentic workflows
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,
Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP
Firewall for AI agents. DLP scanning, SSRF protection, bidirectional MCP scanning, tool poisoning detection, a
Explore other popular mcp server tools:
medusa is AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions & skills before you clone — plus an always-on AI attack-signature scanner and native Rust . It is categorized as a MCP Server with 962 GitHub stars.
medusa is primarily written in Python. It covers topics such as agent-security, ai-security, code-analysis.
You can find installation instructions and usage details in the medusa GitHub repository at github.com/Pantheon-Security/medusa. The project has 962 stars and 153 forks, indicating an active community.
medusa is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to medusa on Agent Skills Hub include agent-audit, node9-proxy, agentic-radar. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: