Skip to content
KitploitKITPLOIT
ToolsBlog
Log in
Submit
ToolsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacyยฉ 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
medusa โ€” AI-first security scanner. NEW in v2026.7: Claude Code compromise detection โ€” vet .claude/ hooks, permissions & skills before you clone โ€” plus an always-on AI attack-signature scanner and native Rust & PHP rules. Also: medusa scan --git to vet any repo, medusa secrets scan for leaked API keys. 40,000+ patterns, zero setup. | Kitploit
Tools/GitHubGitHub/pantheon-security/medusa
Vulnerability ScannersContainer SecurityStatic Code Analysis (SAST)Code AnalysisConfiguration AuditingWeb SecurityCloud SecurityDevSecOpsSecret Detection
Supply Chain Security
AI Security
GitHubpantheon-security/medusa

medusa

View RepositoryWebsite
957156444 months agoReviewed by Kitploit

About

AI-first security scanner. NEW in v2026.7: Claude Code compromise detection โ€” vet .claude/ hooks, permissions & skills before you clone โ€” plus an always-on AI attack-signature scanner and native Rust & PHP rules. Also: medusa scan --git to vet any repo, medusa secrets scan for leaked API keys. 40,000+ patterns, zero setup.

Share

๐Ÿ MEDUSA - AI Security Scanner

PyPI Downloads Python License: AGPL-3.0 Tests Windows macOS Linux

AI-first security scanner with 40,000+ detection patterns for AI/ML, agents, and LLM applications. ๐Ÿค– Works out of the box - no tool installation required. ๐Ÿšจ 200 CVEs: Log4Shell, Spring4Shell, XZ Utils, LangChain RCE, MCP-Remote RCE, React2Shell ๐Ÿ”ฅ medusa scan --git <URL> โ€” Scan any repo for AI supply chain attacks (repo poisoning, prompt injection, MCP tool poisoning) ๐Ÿ” medusa secrets scan โ€” Find leaked API keys in your Claude / Cursor / Copilot / shell history. 21 issuer types. Interactive in-place redaction. ๐Ÿš€ v2026.7.0: Claude Code compromise detection, an always-on AI attack-signature scanner, native Rust & PHP security rules, and rule-level diagnostics โ€” on top of 40,000+ detection patterns.


๐ŸŽฏ What is MEDUSA?

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.

โœจ Key Features

  • ๐Ÿ”ฅ medusa scan --git <URL> - Scan any GitHub repo for AI supply chain attacks in seconds
  • ๐Ÿ” 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, Slackโ€ฆ). Interactive [y/n/s/a/q] purge with mandatory byte-identical backup and JSONL-safe redaction. Local-only, no telemetry.
  • ๐Ÿค– 40,000+ AI Security Patterns - Industry-leading coverage for AI/ML, agents, and LLM applications
  • ๐Ÿ›ก๏ธ Repo Poisoning Detection - Detects weaponized AI editor configs across 28+ file types (Cursor, Cline, Copilot, Claude Code, Gemini, Kiro, and more)
  • ๐Ÿš€ Zero Setup Required - Works immediately after pip install - no tool installation needed
  • ๐Ÿšจ 200 CVE Detections - Log4Shell, Spring4Shell, XZ Utils backdoor, LangChain RCE, MCP remote code execution, React2Shell, and more
  • โšก Parallel Processing - Multi-core scanning (10-40x faster than sequential), works on macOS/Windows/Linux
  • ๐ŸŽจ Beautiful CLI - Rich terminal output with progress bars
  • ๐Ÿง  IDE Integration - Claude Code, Cursor, VS Code, Gemini CLI support
  • ๐Ÿ”„ Smart Caching - Skip unchanged files for lightning-fast rescans (content-hash keyed, correct in CI)
  • โš™๏ธ Configurable - .medusa.yml for project-specific settings
  • ๐ŸŒ Cross-Platform - Native Windows, macOS, and Linux support
  • ๐Ÿ“Š Multiple Reports - JSON, HTML, Markdown, SARIF exports for any workflow
  • ๐Ÿ”ง Optional Linter Support - Auto-detects external linters if installed for enhanced coverage

๐Ÿ†• What's New in v2026.7.0

Claude Code supply-chain detection, broader language coverage, and rule-level observability.

ChangeDetails
๐Ÿ›ก๏ธClaude Code compromise detectionmedusa scan --git now structurally vets .claude/ โ€” poisoned hooks (curl|bash, base64โ†’exec, credential exfil, reverse shells), over-broad permissions (Bash(*), bypassPermissions), wildcard-tool subagents, and dropper skills โ€” before you clone.
๐ŸŽฏAlways-on attack-signature scannerCloses a false-negative gap โ€” jailbreak / prompt-injection payloads in data files (.jsonl/.csv) and prose are now caught regardless of LLM-context confidence, plus invisible-unicode / bidi (Trojan Source, CVE-2021-42574) recovery.
๐Ÿฆ€Native Rust security rules22 out-of-box rules (no toolchain needed) โ€” TLS verification disabled, command injection, untrusted deserialization, raw SQL, unsafe memory ops, weak crypto, SSRF.
๐Ÿ˜Native PHP security rules16 out-of-box rules โ€” SQLi, command/eval injection, LFI/RFI, path traversal, unserialize() object injection, unrestricted upload, reflected XSS, SSRF, weak crypto.
๐Ÿ”ฌRule diagnostics (--trace-rules)Per-rule firing log + timing (rule-trace.jsonl, slow_rules.csv) and a hang-survivable heartbeat โ€” found & fixed a real catastrophic-backtracking ReDoS, plus a ReDoS/nested-set lint that blocks bad patterns at author time.
โšกEngine + accuracyScan-engine perf quick-wins, context-aware screening mode for --git target vetting, large-file byte-cap sampling, and a documentation-placeholder secret-FP fix.
Previous releases

v2026.5.12 โ€” Biggest pattern release: 9,600 โ†’ 40,000+ detection patterns harvested from 8,466 AI-security research papers, false-positive-hardened; structural rule-integrity scanner.

v2026.5.10 โ€” Security hardening: VS Code extension command-injection fix, --fail-on cached-findings bug, tool-cache stale-path fix, user-home MCP configs made opt-in.

v2026.5.9 โ€” Agentic-commerce coverage: UCPScanner + AP2Scanner + 45 hand-tuned positive-pattern rules.

v2026.5.8 โ€” medusa secrets: scan AI chat & shell histories for leaked credentials (21 issuer types) with interactive [y/n/s/a/q] purge.

v2026.5.7 โ€” Indirect PI rules (101/102), supply chain import scanner, macOS/Windows multiprocessing fix.

v2026.5.5 โ€” security hardening release (argv injection defenses, git SSRF, HMAC cache integrity, markdown XSS fix).

External Linters (optional): MEDUSA auto-detects bandit, eslint, shellcheck, etc. if installed. See Optional Tools Guide.


๐Ÿ” Scan your AI chat history for leaked secrets

Your PyPI token might be in your Claude chat history right now.

Developers paste API keys, tokens, and credentials into AI assistants every day โ€” "deploy this with pypi-AgEI...", "use my ghp_... to push", "the AWS key is AKIA...". The assistants keep those conversations in plaintext on disk. Anyone with read access to $HOME โ€” or any future malware with shell access โ€” can grep -r 'sk-\|ghp_\|AKIA' ~/ and harvest production credentials in seconds.

medusa secrets scan finds them. medusa secrets purge cleans them up.

30-second tour

medusa secrets scan
Scanning 118 file(s)...

โ”€โ”€ claude-code โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
/home/ross/.claude/history.jsonl  (13 finding(s))
[CRITICAL] Anthropic API key (anthropic)
    /home/ross/.claude/history.jsonl:1005:13
    sk-ant-api03***...***
[CRITICAL] PyPI API token (pypi)
    /home/ross/.claude/history.jsonl:125:94
    pypi-AgEIc***...***
[CRITICAL] GitHub fine-grained PAT (github)
    /home/ross/.claude/history.jsonl:2306:13
    github_pat_11A***...***
[HIGH]     HuggingFace token (huggingface)
    /home/ross/.claude/history.jsonl:3387:13
    hf_JOi***...***
...

Total: 13 credentials across 1 file(s).
Report:  /home/ross/.medusa/secrets-scan/secrets-20260519-074452.json
medusa secrets purge
Download Tool

Most Popular

View all โ†’

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    ๐ŸŽฏ The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    755
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    510
  • 3

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    415
  • 4

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    343
  • 5

    antifox

    antifox-ai/antifox

    AI multi-agent autonomous penetration testing platform that runs recon, attack-surface discovery, exploitation validation and evidence-backed report delivery.

    259
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurityโ€”where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    258

Explore all tools

Browse our collection of tools

View all tools โ†’