AI Agent Vulnerability Scanning AI Agents

Tools and platforms for detecting, auditing, and testing security vulnerabilities in AI agents, MCP servers, and their configurations through static analysis, dynamic testing, and threat intelligence. Does NOT include general application security, smart contract auditing (unless agent-specific), or dependency vulnerability scanning.

There are 104 ai agent vulnerability scanning agents tracked. 5 score above 50 (established tier). The highest-rated is AgentSeal/agentseal at 66/100 with 119 stars and 2,149 monthly downloads.

Get all 104 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=agents&subcategory=ai-agent-vulnerability-scanning&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

# Agent Score Tier
1 AgentSeal/agentseal

Security toolkit for AI agents. Scan your machine for dangerous skills and...

66
Established
2 Nebulock-Inc/agentic-threat-hunting-framework

ATHF is a framework for agentic threat hunting - building systems that can...

64
Established
3 HeadyZhang/agent-audit

Static security scanner for LLM agents β€” prompt injection, MCP config...

52
Established
4 affaan-m/agentshield

AI agent security scanner. Detect vulnerabilities in agent configurations,...

50
Established
5 LucidAkshay/kavach

Tactical AI Workspace Monitor & EDR

50
Established
6 cosai-oasis/secure-ai-tooling

The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating...

49
Emerging
7 PurpleAILAB/Vigilo

An AI hacker for Web3 Smart Contract. for bug bounties, Audit contest,...

47
Emerging
8 oasm-platform/open-asm

Open-source platform for cybersecurity Attack Surface Management (OASM).

47
Emerging
9 Defend-AI-Tech-Inc/agent-discover-scanner

Multi-layer AI agent detection: Static code analysis, network monitoring,...

43
Emerging
10 AgentSecOps/SecOpsAgentKit

Security operations toolkit for AI coding agents. Give Claude Code 25+...

41
Emerging
11 roli-lpci/little-canary

Sacrificial LLM instances as behavioral probes for prompt injection detection

41
Emerging
12 ThirdKeyAI/agentsniff

Detect AI agents operating on your network through passive monitoring,...

40
Emerging
13 opena2a-org/opena2a

Open-source security tools for AI agents. Find vulnerabilities, fix root...

39
Emerging
14 angelnicolasc/drako

AI agent security platform. Scan before you deploy. Block in runtime. No...

38
Emerging
15 ousher/tia-framework

🐍 TIA β€” Threat Intelligence Autonomy | 26 AI agents detect threats in 12...

38
Emerging
16 mickmicksh/chub-supply-chain-poc

Silent dependency injection through AI documentation pipelines. 240...

37
Emerging
17 aiconnai/agentshield

Security scanner for AI agent extensions β€” offline-first, multi-framework,...

36
Emerging
18 Agent-Field/sec-af

AI-native security auditor on AgentField that proves exploitability with...

36
Emerging
19 math280h/safe-pkgs

Package safety checks for AI agents before install via MCP

36
Emerging
20 thebearwithabite/membranes

πŸ›‘οΈ The VirusTotal for prompt injection β€” open-source defense with...

36
Emerging
21 sundew-sh/sundew

A carnivorous honeypot for AI agents. Every deployment generates a unique...

36
Emerging
22 gapilongo/SOC

Intelligent SOC automation framework powered by LangGraph multi-agent...

35
Emerging
23 NewmanXBT/sealevel-guard

Agent-native Solana security infrastructure for pre-deployment,...

35
Emerging
24 GH05TCREW/eidolon

Network scanner that maps infrastructure into a Neo4j graph and executes...

34
Emerging
25 pantheraudits/web3-sec-ai-prompts

AI prompts for web3 security researchers β€” bug bounties, private audits, and contests

32
Emerging
26 oasm-platform/oasm-assistant

Smart assistant for threat monitoring, attack prevention, and web protection.

30
Emerging
27 Defenter-AI/defenter-proxy

Real-time semantic security for AI coding agents and MCP tools.

30
Emerging
28 n-WN/SubgroupX

正规子羀.AI Agent | SubgroupX: A high-performance AI Agent for offensive...

30
Emerging
29 proventra/proventra-core

Secure your AI Agents against prompt injection attacks

29
Experimental
30 Nomadu27/InsAIts

Runtime security layer for multi-agent AI. 23 anomaly types. OWASP MCP Top...

27
Experimental
31 waris206/ThreatLens

AI-Driven Malware Triage & Deep Swarm Inspection Platform

26
Experimental
32 limaronaldo/agentshield

Security scanner for AI agent extensions β€” offline-first, multi-framework,...

25
Experimental
33 spiffy-oss/artguard

Open-source AI artifact scanner. Detect malicious agent skills, MCP servers,...

25
Experimental
34 vigilhq/vigil

The compliance ops agent that never sleeps β€” watches regulatory feeds, maps...

24
Experimental
35 VolkanSah/AI-API-Security-Best-Practices

The purpose of this document is to outline the security risks and...

24
Experimental
36 scthornton/securecode-web

Real-World Security Conversations for AI Training

23
Experimental
37 blairmichaelg/secbrain

Multi-agent AI security bounty system with DeFi exploit protection...

23
Experimental
38 LuciferForge/prompt-shield

Lightweight prompt injection detector. 22 attack patterns. Blocks jailbreaks...

23
Experimental
39 fobi28/Secure-Agent-Launcher

Block AI agent access to sensitive macOS paths and log all actions to...

23
Experimental
40 jakyunknown/SCEP-AI

SCEP AI is a open-sourced ai password entropy checker app that checks how...

23
Experimental
41 peg/snare

Honeypot canaries for AI agents. Detect compromised agents via fake...

23
Experimental
42 jitendar-singh/securitymind

Security Mind: AI-Powered Application Security Posture Management (ASPM) Platform

23
Experimental
43 luckyPipewrench/pipelock-rules

Official community detection rules for Pipelock - the open-source agent firewall

23
Experimental
44 JohnField07/AI-Bastion

Protect autonomous AI agents on Linux with AI-Bastion’s 8-layer security...

22
Experimental
45 SayedhDev/AI-Bastion-Guardian

Protect Windows hosts running AI agents by enforcing firewall rules,...

22
Experimental
46 Enzonogue/opena2a

Manage and secure AI agents by scanning, protecting, benchmarking, and...

22
Experimental
47 Jadevil73/agentseal

Detect vulnerabilities in AI agents by testing their security to prevent...

22
Experimental
48 Deaxu/ArchGraph

Security-first code intelligence for AI agents β€” taint analysis, CVE...

22
Experimental
49 kogunlowo123/ai-agent-soc-triage

AI-powered SOC alert triage agent with MITRE ATT&CK classification, severity...

22
Experimental
50 decoy-run/decoy-scan

Security scanner for MCP server configurations. Finds risky tools, detects...

22
Experimental
51 Zorropiscina/artguard

Scan AI artifacts like agent skills and config files for security risks,...

22
Experimental
52 maxwalser001-del/shieldpilot

Open-source security platform for AI coding agents. 9 risk analyzers, 178+...

22
Experimental
53 DebasishTripathy13/Project-Libra

This project is completely linked to all cyber sec tool from me as a sec enthusiast.

22
Experimental
54 huyairobot/neox-agent-risk-lab

Simulate AI agent attack scenarios to test governance, compliance, and...

22
Experimental
55 speed785/sentinel-inject

Prompt injection scanner middleware for AI agents β€” dual-layer rule-based +...

22
Experimental
56 ShaggyT0701/prompt-shield

πŸ›‘οΈ Detect and block prompt injection attacks in LLM apps using pattern...

22
Experimental
57 panguard-ai/panguard-ai

Open-source security platform for AI agents -- audits skills before install,...

22
Experimental
58 elliotllliu/agent-shield

πŸ›‘οΈ Security scanner for AI agents, MCP servers & plugins β€” 30 rules, AST...

22
Experimental
59 autralabs/agentshield

AgentShield is a middleware implementation of Zero Shot Embedding Drift...

22
Experimental
60 raghulvj01/aegis-mcp

πŸ›‘οΈ Open-source MCP server for AI-powered DevSecOps β€” cloud audits, CVE...

22
Experimental
61 TheIbrahimMalik/vendiligence

Vertical AI agent workflow for vendor due diligence and security...

22
Experimental
62 vectimus/policies

78 Cedar policies and 369 rules governing AI coding agents. Every rule...

22
Experimental
63 Mkar9182/SCEP-AI

Protect passwords with a fast, standalone HTML tool that runs locally, using...

22
Experimental
64 PowerHouse-Consulting-Group/cybersecurity-analyst-agent

πŸ›‘οΈ Autonomous AI Cybersecurity Log Analyst. An LLM-Agnostic SOC agent...

22
Experimental
65 lahadiyani/secai-prototype-lite-version

SECAI adalah kerangka kerja (framework) eksperimental yang...

21
Experimental
66 usestackbox/anticipator

Anticipator is an open-source threat detection platform for multi-agent AI systems.

21
Experimental
67 brianleach/cyrusworker

Run Cyrus (Claude Code-powered Linear agent) on Cloudflare's edge...

21
Experimental
68 mark0011astra/Secure-Agent-Launcher

Blocks risky AI CLI runs before they access secrets like ~/.ssh, ~/.aws, and...

20
Experimental
69 Perkins-Fund/Cortex-Agent-Source

Traceix Cortex Agents. Malware analysis for everyone

20
Experimental
70 Nezar-Alhammadi/Vigil-AI

Vigil-AI: An autonomous Web3 security auditor

20
Experimental
71 VektorSecurity/ai-cybersecurity-homelab

Welcome to my Cybersecurity Homelab, where I experiment with ethical...

20
Experimental
72 GravityZenAI/AI-Bastion-Guardian

Windows-side security for AI agents running in WSL2. Firewall rules, egress...

20
Experimental
73 AIDEUSPRO/mandatory-behavioral-firewall

πŸ›‘οΈ AI Code Quality Control System for Cursor IDE - Prevents low-quality code...

20
Experimental
74 Milbaxter/prompt-shield

AI agent security oracle. Scan any message for prompt injections. Pay with...

19
Experimental
75 stlas/PromptShield

Prompt Injection Firewall for AI agents. 113 detection patterns, 14 threat...

19
Experimental
76 empowered-humanity/agent-security

AI agent security scanner β€” 176 detection patterns with taint analysis,...

19
Experimental
77 stubbies/next-ai-shield

The easiest way to protect your Next.js content from AI crawlers. Shield...

19
Experimental
78 chirayu999/infinity-veil

Multi Agent system to hunt for cyber threats in an organisation's infrastructure

19
Experimental
79 SecurityLab-UCD/ai-agent-security

[RAIE'25] This repository contains source code for the demos and attacks we...

18
Experimental
80 chevyphillip/auggiesec-agent

AI-powered security scanner that analyzes codebases for OWASP Top 10 2021...

18
Experimental
81 montevive/prompt-injection-demo

Prompt Injection Demo with n8n

16
Experimental
82 brunosergi/tldr-threat-reports

An AI-automated tool designed to help Threat Intelligence (CTI) Analysts...

15
Experimental
83 Moraa1714/MSEP

🌌 Enhance digital intelligence with M.S.E.P., an AI-powered tool that deeply...

15
Experimental
84 uncensored-waterford179/mguard

Protect AI agent memory from poisoning attacks with a zero-dependency shield...

15
Experimental
85 Tyleshancloud7/Tyleshancloud7

About me

14
Experimental
86 abhinav8925/AI-Dependency-Risk-Analyzer

AI-powered scanner detecting vulnerabilities, license issues, and...

14
Experimental
87 dryssboy/Tyleshancloud7

πŸ” Explore hands-on cybersecurity projects focused on GRC, cloud security,...

14
Experimental
88 MinSeok-log/cognitive-injection

A new class of npm attack vector that bypasses all static security scanners...

14
Experimental
89 vishalbk/mvt-trilogy

MVT Observatory β€” Macro Vulnerability Trilogy. AI-native FinTech risk...

14
Experimental
90 noobdna/tacomachi-agent

AI agent "Tacomachi" for security, automation, and network intelligence

14
Experimental
91 SatishoBananamoto/vigil

Predictive risk intelligence for open source dependencies

14
Experimental
92 HelloNathan9999/permission-patrol

πŸ›‘οΈ Inspect Python scripts before execution to prevent hidden destructive...

14
Experimental
93 KONGMatta/sentinel-web3-audit-bot

πŸš€ Ultimate Web3 Security AI Bot 2026 – Free Autonomous Audit Toolkit for...

14
Experimental
94 ajmelian/HeaderGuard

HeaderGuard (PHP 8.4) audita cabeceras de seguridad HTTP y hace quick check...

13
Experimental
95 andrewkolagit/DetectPack-Forge

DetectPack Forge turns plain-English behaviors or sample logs into...

13
Experimental
96 MRFrazer25/AI-OSINT-Security-Analyzer

AI Cybersecurity intelligence gathering streamlit web app using Cohere's...

12
Experimental
97 khushiiagrawal/Adaptive-Threat-Modeler

Adaptive Threat Modeler is security analysis platform that continuously...

12
Experimental
98 patbi/AI_Security_Engineers_Roadmap

AI_Security_Engineers_Roadmap

11
Experimental
99 eyalgerman/KubeSecAgent

KubeSecAgent is an agent-based system for automated detection and...

11
Experimental
100 JadeGate/jadegate

πŸ’  The security scanner for AI agents. 5-layer verification for MCP servers &...

11
Experimental
101 yasir23/vigil

Autonomous threat intelligence agent for the terminal. Hunt threats,...

11
Experimental
102 Caleb22187/agentshield

Free browser-based prompt injection scanner for AI agents. 9 detection...

11
Experimental
103 cerberus-watch/cerberus-agents

Cerberus MindStudio Agents for various security tasks

11
Experimental
104 Param-10/cybersec-ai-agent

AI-powered cybersecurity assistant built on Cloudflare

11
Experimental

Comparisons in this category