Prompt Injection Security Prompt Engineering Tools

Tools for detecting, testing, and defending against prompt injection attacks, jailbreaks, and adversarial prompts targeting LLMs. Does NOT include general LLM security, data poisoning defenses unrelated to prompts, or prompt engineering best practices.

There are 105 prompt injection security tools tracked. 1 score above 70 (verified tier). The highest-rated is protectai/llm-guard at 74/100 with 2,660 stars and 329,796 monthly downloads.

Get all 105 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=prompt-engineering&subcategory=prompt-injection-security&limit=20"

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

#	Tool	Score	Tier	Stars	Language
1	protectai/llm-guard The Security Toolkit for LLM Interactions	74	Verified	2,660	Python
2	MaxMLang/pytector Easy to use LLM Prompt Injection Detection / Detector Python Package with...	63	Established	38	Python
3	agencyenterprise/PromptInject PromptInject is a framework that assembles prompts in a modular fashion to...	48	Emerging	465	Python
4	Resk-Security/Resk-LLM Resk is a robust Python library designed to enhance security and manage...	47	Emerging	16	Python
5	utkusen/promptmap a security scanner for custom LLM applications	44	Emerging	1,146	Python
6	Dicklesworthstone/acip The Advanced Cognitive Inoculation Prompt	43	Emerging	300	Shell
7	TrustAI-laboratory/Learn-Prompt-Hacking This is The most comprehensive prompt hacking course available, which record...	38	Emerging	271	Jupyter Notebook
8	protectai/rebuff LLM Prompt Injection Detector	38	Emerging	1,439	TypeScript
9	jailbreakme-xyz/jailbreak jailbreakme.xyz is an open-source decentralized app (dApp) where users are...	38	Emerging	45	JavaScript
10	SemanticBrainCorp/SemanticShield The Security Toolkit for managing Generative AI(especially LLMs) and...	37	Emerging	22	Python
11	Hellsender01/prompt-injection-taxonomy A structured reference covering 253 prompt injection techniques across 17...	37	Emerging	2	—
12	LostOxygen/llm-confidentiality Whispers in the Machine: Confidentiality in Agentic Systems	36	Emerging	42	Python
13	Repello-AI/whistleblower Whistleblower is a offensive security tool for testing against system prompt...	36	Emerging	149	Python
14	MindfulwareDev/PromptProof Plug-and-play guardrail prompts for any LLM — injection defense,...	35	Emerging	1	Python
15	Code-and-Sorts/PromptDrifter 🧭 PromptDrifter – one‑command CI guardrail that catches prompt drift and...	34	Emerging	7	Python
16	alphasecio/prompt-guard A web app for testing Prompt Guard, a classifier model by Meta for detecting...	34	Emerging	3	Python
17	yunwei37/prompt-hacker-collections prompt attack-defense, prompt Injection, reverse engineering notes and...	34	Emerging	295	—
18	Xayan/Rules.txt A rationalist ruleset for "debugging" LLMs, auditing their internal...	34	Emerging	80	—
19	cysecbench/dataset Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking...	33	Emerging	33	Python
20	trinib/ZORG-Jailbreak-Prompt-Text Bypass restricted and censored content on AI chat prompts 😈	32	Emerging	245	—
21	genia-dev/vibraniumdome LLM Security Platform.	31	Emerging	26	Python
22	CyberAlbSecOP/MINOTAUR_Impossible_GPT_Security_Challenge MINOTAUR: The STRONGEST Secure Prompt EVER! Prompt Security Challenge,...	31	Emerging	25	—
23	takashiishida/cleanprompt Anonymize sensitive information in text prompts before sending them to LLM...	31	Emerging	20	Python
24	Arash-Mansourpour/Breaking-LLaMA-Limitations-for-DAN An educational and research-based exploration into breaking the limitations...	31	Emerging	5	—
25	user1342/Folly Open-source LLM Prompt-Injection and Jailbreaking Playground	31	Emerging	30	Python
26	akazah/prompt-anonymizer Anonymize / mask personal information before sending prompts to chat AI...	29	Experimental	22	Python
27	M507/HackMeGPT Vulnerable LLM Application	29	Experimental	14	Python
28	Addy-shetty/Pitt PITT is an open‑source, OWASP‑aligned LLM security scanner that detects...	28	Experimental	3	Python
29	forcesunseen/llm-hackers-handbook A guide to LLM hacking: fundamentals, prompt injection, offense, and defense	27	Experimental	188	—
30	hugobatista/unicode-injection Proof of concept demonstrating Unicode injection vulnerabilities using...	27	Experimental	5	—
31	LLMPID/LLMPID-AS LLM Prompt Injection Detection API Service PoC.	27	Experimental	10	Go
32	HumanCompatibleAI/tensor-trust A prompt injection game to collect data for robust ML research	27	Experimental	67	Python
33	2alf/prmptinj Curated + custom prompt injections.	26	Experimental	4	—
34	langguard/langguard-python LangGuard Python Library	26	Experimental	2	Python
35	arekusandr/last_layer Ultra-fast, low latency LLM prompt injection/jailbreak detection ⛓️	26	Experimental	125	Python
36	davidegat/happy-prompts Utterly unelegant prompts for local LLMs, with scary results.	25	Experimental	24	—
37	kennethleungty/ARTKIT-Gandalf-Challenge Exposing Jailbreak Vulnerabilities in LLM Applications with ARTKIT	25	Experimental	4	Jupyter Notebook
38	BlackTechX011/HacxGPT-Jailbreak-prompts HacxGPT Jailbreak 🚀: Unlock the full potential of top AI models like...	25	Experimental	155	—
39	crodjer/biip Strip out PII before Sending Data	25	Experimental	7	Rust
40	jagan-raj-r/appsec-prompt-cheatsheet A curated collection of high-quality prompts to help AppSec engineers use...	24	Experimental	1	—
41	LoonMORTI/promptshield 🛡️ Protect LLM applications with PromptShields, a robust security framework...	24	Experimental	—	Python
42	promptshieldhq/promptshield-engine Detection and anonymization microservice for the PromptShield stack.	24	Experimental	2	Python
43	AmanPriyanshu/FRACTURED-SORRY-Bench-Automated-Multishot-Jailbreaking FRACTURED-SORRY-Bench: This repository contains the code and data for the...	24	Experimental	4	Python
44	SurceBeats/GhostInk Emoji steganography tool that hides secret text inside emojis using Unicode...	24	Experimental	9	JavaScript
45	Sushegaad/Semantic-Privacy-Guard Semantic Privacy Guard: A Java middleware that intercepts text, identifies...	23	Experimental	1	HTML
46	TechJackSolutions/GAIO Open-source guardrail standard for reducing AI fabrication and improving...	23	Experimental	1	HTML
47	deepanshu-maliyan/guardrails-for-ai-coders Security prompts and checklists for AI coding assistants. One command...	23	Experimental	1	PowerShell
48	yangyihe0305-droid/llm-red-team-research Systematic exploration of LLM alignment boundaries through logical stress testing	23	Experimental	1	Shell
49	tamadip007/getSPNless 🔍 Obtain Kerberos service tickets effortlessly using the SPN-less technique...	22	Experimental	—	Python
50	Georgeyoussef066/promptshield 🛡️ Secure your LLM applications with PromptShields, a framework designed for...	22	Experimental	—	Python
51	ajaakevin/HACKME Explore and analyze WhatsApp data using open-source OSINT tools designed for...	22	Experimental	—	Python
52	AraLeo5/Semantic-Privacy-Guard Identify and protect personal data in text by intercepting and masking PII...	22	Experimental	—	HTML
53	rb81/prompt-hacking-classifier A flexible and portable solution that uses a single robust prompt and...	22	Experimental	16	Jupyter Notebook
54	AdityaBhatt3010/Hacking-Lakera-Gandalf-AI-via-Prompt-Injection Lakera Gandalf AI challenge's step by step walkthrough, showcasing...	22	Experimental	13	—
55	Unknown-2829/llm-prompt-engineering A collection of prompt engineering and red-teaming experiments with large...	21	Experimental	2	—
56	promptinjection/promptinjection.github.io Contributed by Community	21	Experimental	2	HTML
57	Eulex0x/cleanmyprompt A transparent, local-only tool to sanitize sensitive info for AI.	21	Experimental	2	HTML
58	amk9978/Guardian The LLM guardian kernel	20	Experimental	10	Go
59	yksanjo/promptshield 🛡️ AI prompt security and validation tool to protect against prompt injection attacks	20	Experimental	1	Python
60	tuxsharxsec/Jailbreaks A repo for all the jailbreaks	20	Experimental	39	Roff
61	Ethan-YS/PromptGuard-for-Agents 🛡️ Universal AI defense framework protecting agents from prompt injection...	20	Experimental	1	Python
62	grasses/PoisonPrompt Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language...	20	Experimental	20	Python
63	KazKozDev/system-prompt-benchmark Test your LLM system prompts against 287 real-world attack vectors including...	20	Experimental	11	Python
64	AiShieldsOrg/AiShieldsWeb AiShields is an open-source Artificial Intelligence Data Input and Output Sanitizer	19	Experimental	3	Python
65	sruzima/safe-gamer-helper-chatbot System prompt for SafeGamer Helper, an AI chatbot that teaches kids online...	19	Experimental	—	—
66	successfulstudy/jailbreakprompt Compile a list of AI jailbreak scenarios for enthusiasts to explore and test.	19	Experimental	44	—
67	promptslab/LLM-Prompt-Vulnerabilities Prompts Methods to find the vulnerabilities in Generative Models	19	Experimental	20	—
68	anuraag-khare/prompt-fence A Python SDK (backed by Rust) for establishing cryptographic security...	19	Experimental	—	Python
69	ianreboot/safeprompt Protect AI automations from prompt injection attacks. One API call stops...	19	Experimental	—	TypeScript
70	apologetik/CyberPrompts A collection of Large Language Model (LLM) prompts helpful for various...	19	Experimental	—	—
71	anishrajpandey/Prompt_Injection_Detector A lightweight web tool to detect prompt injection in AI inputs. Helps...	17	Experimental	1	HTML
72	asif-hanif/baple [MICCAI 2024] Official code repository of paper titled "BAPLe: Backdoor...	17	Experimental	56	Python
73	liangzid/PromptExtractionEval Source code of the paper "Why Are My Prompts Leaked? Unraveling Prompt...	16	Experimental	7	Python
74	5ynthaire/5YN-LiveWebpageScanPrecision-Prompt Prompt forces direct, real-time retrieval of unaltered text from URLs with...	16	Experimental	1	—
75	IAHASH/iahash IA-HASH: A simple, universal way to verify that an AI truly generated a...	16	Experimental	1	Python
76	astecka-m/AgentGuard Protect AI agents by detecting and blocking prompt, command injection,...	15	Experimental	1	Python
77	SafellmHub/hguard-go Guardrails for LLMs: detect and block hallucinated tool calls to improve...	15	Experimental	7	Go
78	obscuralabs-AI/Symbolic-Prompt-PenTest Semantic Stealth Attacks & Symbolic Prompt Red Teaming on GPT and other LLMs.	15	Experimental	8	—
79	pastsafe-ext/pastesafe Chrome extension that prevents leaking API keys and sensitive data into AI chats	14	Experimental	—	HTML
80	alexandrughinea/prompt-chainmail-ts Security middleware that shields AI applications from prompt injection,...	14	Experimental	3	TypeScript
81	Kimosabey/sentinel-layer AI Safety, Governance, and Security Layer featuring advanced Prompt...	14	Experimental	—	—
82	yeraydoblasbueno/llm-security-framework Testing LLM vulnerabilities (Jailbreaks, Prompt Injections) locally using...	14	Experimental	—	Jupyter Notebook
83	khaal10460/sentinel-trace Full-stack AI data ingestion pipeline with real-time adversarial filtering,...	14	Experimental	—	Python
84	ndpvt-web/aristotelian-compliance-test When Aristotle gets a LinkedIn account and starts red-teaming LLMs....	14	Experimental	—	—
85	jyotisin/secure-llm-gateway Secure large language model access by enforcing role-based controls,...	14	Experimental	—	—
86	bhargavi852004/Safe-Scope Safe Scope is a real-time, explainable AI platform that monitors online...	14	Experimental	3	Python
87	sachnaror/prompt-guardrails-engine Production-grade FastAPI microservice that forces LLMs to behave....	14	Experimental	—	Python
88	bcdannyboy/PromptMatryoshka Multi-Provider LLM Jailbreak Research Framework	14	Experimental	12	Python
89	Pro-GenAI/Smart-Prompt-Eval Evaluating LLM Robustness with Manipulated Prompts	14	Experimental	4	Python
90	valentinaschiavon99/promptguard PromptGuard · LLM Prompt Risk Analyzer · Project for "Neuere Methoden in der...	13	Experimental	—	HTML
91	thatgeeman/prompt-injection-cv PoC for prompt injection attacks on LLMs in recruitment. Tests Gemini's...	13	Experimental	2	TeX
92	thepratikguptaa/prompt-injection This repository serves as a comprehensive resource for understanding and...	12	Experimental	1	Python
93	Tarunjit45/PromptGuard PromptGuard is a pragmatic, opinionated framework for establishing...	12	Experimental	1	Python
94	Mousewarriors/Cybersecurity-Portfolio I built and documented hands-on cybersecurity projects focused on SOC...	12	Experimental	1	Python
95	coollane925/AI-FUNDAMENTALS-AND-PROBING This is a beginner-intermediate level report for people who are interested...	11	Experimental	—	—
96	SolsticeMoon/Spectre_Steganography_System An experiment in LLM-Assisted steganography using zero-width text.	11	Experimental	—	—
97	best247team1-cloud/Ai-shield-pro AI Shield Pro: A secure privacy tool to redact sensitive data and engineer...	11	Experimental	—	HTML
98	PMQ9/Ordo-Maledictum-Promptorum Researching a system for preventing prompt injection by separating user...	11	Experimental	—	Rust
99	wmjg-alt/ai_security_ demo of an ai security failure, prompt injection	11	Experimental	—	JavaScript
100	yogeshwankhede007/WebSec-AI WebSec-AI: A toolkit that combines AI and cybersecurity techniques to detect...	11	Experimental	—	Python
101	seamus-brady/promptbouncer A prototype defense against prompt-based attacks with real-time threat assessment.	11	Experimental	—	Python
102	PrithikaGopinath/DataGuardian-AI-Privacy-Coach AI-powered privacy coach with risk detection, scenario analysis, and...	11	Experimental	—	—
103	gkanellopoulos/prompthorizon Python library that enables developers to anonymize JSON objects by creating...	10	Experimental	1	Python
104	vladutdinu/prompty-api PromptyAPI, people's LLM-based applications security layer	10	Experimental	1	Python
105	nodite/llm-guard-ts The Security Toolkit for LLM Interactions (TS version)	10	Experimental	1	—

Comparisons in this category

llm-guard and promptmap (74 vs 44) llm-guard and llm-confidentiality (74 vs 36) llm-guard and pytector (74 vs 63) llm-guard and SemanticShield (74 vs 37) llm-guard and Resk-LLM (74 vs 47) llm-guard and PromptProof (74 vs 35) pytector and PromptProof (63 vs 35)