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 102 prompt injection security tools tracked. 5 score above 50 (established tier). The highest-rated is protectai/llm-guard at 65/100 with 2,660 stars.

Get all 102 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	65	Established	2,660	Python
2	MaxMLang/pytector Easy to use LLM Prompt Injection Detection / Detector Python Package with...	62	Established	38	Python
3	utkusen/promptmap a security scanner for custom LLM applications	51	Established	1,146	Python
4	agencyenterprise/PromptInject PromptInject is a framework that assembles prompts in a modular fashion to...	51	Established	465	Python
5	Resk-Security/Resk-LLM Resk is a robust Python library designed to enhance security and manage...	50	Established	16	Python
6	Dicklesworthstone/acip The Advanced Cognitive Inoculation Prompt	49	Emerging	300	Shell
7	protectai/rebuff LLM Prompt Injection Detector	45	Emerging	1,439	TypeScript
8	LostOxygen/llm-confidentiality Whispers in the Machine: Confidentiality in Agentic Systems	43	Emerging	42	Python
9	TrustAI-laboratory/Learn-Prompt-Hacking This is The most comprehensive prompt hacking course available, which record...	43	Emerging	271	Jupyter Notebook
10	Repello-AI/whistleblower Whistleblower is a offensive security tool for testing against system prompt...	43	Emerging	149	Python
11	jailbreakme-xyz/jailbreak jailbreakme.xyz is an open-source decentralized app (dApp) where users are...	41	Emerging	45	JavaScript
12	MindfulwareDev/PromptProof Plug-and-play guardrail prompts for any LLM — injection defense,...	41	Emerging	1	Python
13	alphasecio/prompt-guard A web app for testing Prompt Guard, a classifier model by Meta for detecting...	41	Emerging	3	Python
14	SemanticBrainCorp/SemanticShield The Security Toolkit for managing Generative AI(especially LLMs) and...	41	Emerging	22	Python
15	yunwei37/prompt-hacker-collections prompt attack-defense, prompt Injection, reverse engineering notes and...	41	Emerging	295	—
16	cysecbench/dataset Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking...	40	Emerging	33	Python
17	Xayan/Rules.txt A rationalist ruleset for "debugging" LLMs, auditing their internal...	40	Emerging	80	—
18	trinib/ZORG-Jailbreak-Prompt-Text Bypass restricted and censored content on AI chat prompts 😈	39	Emerging	245	—
19	user1342/Folly Open-source LLM Prompt-Injection and Jailbreaking Playground	38	Emerging	30	Python
20	Code-and-Sorts/PromptDrifter 🧭 PromptDrifter – one‑command CI guardrail that catches prompt drift and...	38	Emerging	7	Python
21	genia-dev/vibraniumdome LLM Security Platform.	38	Emerging	26	Python
22	takashiishida/cleanprompt Anonymize sensitive information in text prompts before sending them to LLM...	38	Emerging	20	Python
23	CyberAlbSecOP/MINOTAUR_Impossible_GPT_Security_Challenge MINOTAUR: The STRONGEST Secure Prompt EVER! Prompt Security Challenge,...	38	Emerging	25	—
24	M507/HackMeGPT Vulnerable LLM Application	36	Emerging	14	Python
25	Hellsender01/prompt-injection-taxonomy A structured reference covering 253 prompt injection techniques across 17...	36	Emerging	2	—
26	hugobatista/unicode-injection Proof of concept demonstrating Unicode injection vulnerabilities using...	34	Emerging	5	—
27	Arash-Mansourpour/Breaking-LLaMA-Limitations-for-DAN An educational and research-based exploration into breaking the limitations...	34	Emerging	5	—
28	Addy-shetty/Pitt PITT is an open‑source, OWASP‑aligned LLM security scanner that detects...	34	Emerging	3	Python
29	LLMPID/LLMPID-AS LLM Prompt Injection Detection API Service PoC.	34	Emerging	10	Go
30	HumanCompatibleAI/tensor-trust A prompt injection game to collect data for robust ML research	34	Emerging	67	Python
31	forcesunseen/llm-hackers-handbook A guide to LLM hacking: fundamentals, prompt injection, offense, and defense	34	Emerging	188	—
32	arekusandr/last_layer Ultra-fast, low latency LLM prompt injection/jailbreak detection ⛓️	33	Emerging	125	Python
33	crodjer/biip Strip out PII before Sending Data	32	Emerging	7	Rust
34	BlackTechX011/HacxGPT-Jailbreak-prompts HacxGPT Jailbreak 🚀: Unlock the full potential of top AI models like...	32	Emerging	155	—
35	kennethleungty/ARTKIT-Gandalf-Challenge Exposing Jailbreak Vulnerabilities in LLM Applications with ARTKIT	32	Emerging	4	Jupyter Notebook
36	akazah/prompt-anonymizer Anonymize / mask personal information before sending prompts to chat AI...	32	Emerging	22	Python
37	AmanPriyanshu/FRACTURED-SORRY-Bench-Automated-Multishot-Jailbreaking FRACTURED-SORRY-Bench: This repository contains the code and data for the...	31	Emerging	4	Python
38	davidegat/happy-prompts Utterly unelegant prompts for local LLMs, with scary results.	31	Emerging	24	—
39	jagan-raj-r/appsec-prompt-cheatsheet A curated collection of high-quality prompts to help AppSec engineers use...	30	Emerging	1	—
40	2alf/prmptinj Curated + custom prompt injections.	29	Experimental	4	—
41	rb81/prompt-hacking-classifier A flexible and portable solution that uses a single robust prompt and...	29	Experimental	16	Jupyter Notebook
42	Unknown-2829/llm-prompt-engineering A collection of prompt engineering and red-teaming experiments with large...	27	Experimental	2	—
43	promptinjection/promptinjection.github.io Contributed by Community	27	Experimental	2	HTML
44	amk9978/Guardian The LLM guardian kernel	27	Experimental	10	Go
45	AdityaBhatt3010/Hacking-Lakera-Gandalf-AI-via-Prompt-Injection Lakera Gandalf AI challenge's step by step walkthrough, showcasing...	27	Experimental	13	—
46	grasses/PoisonPrompt Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language...	27	Experimental	20	Python
47	AiShieldsOrg/AiShieldsWeb AiShields is an open-source Artificial Intelligence Data Input and Output Sanitizer	26	Experimental	3	Python
48	successfulstudy/jailbreakprompt Compile a list of AI jailbreak scenarios for enthusiasts to explore and test.	26	Experimental	44	—
49	SurceBeats/GhostInk Emoji steganography tool that hides secret text inside emojis using Unicode...	26	Experimental	9	JavaScript
50	tuxsharxsec/Jailbreaks A repo for all the jailbreaks	26	Experimental	39	Roff
51	promptslab/LLM-Prompt-Vulnerabilities Prompts Methods to find the vulnerabilities in Generative Models	26	Experimental	20	—
52	anishrajpandey/Prompt_Injection_Detector A lightweight web tool to detect prompt injection in AI inputs. Helps...	24	Experimental	1	HTML
53	asif-hanif/baple [MICCAI 2024] Official code repository of paper titled "BAPLe: Backdoor...	24	Experimental	56	Python
54	yksanjo/promptshield 🛡️ AI prompt security and validation tool to protect against prompt injection attacks	24	Experimental	1	Python
55	promptshieldhq/promptshield-engine Detection and anonymization microservice for the PromptShield stack.	24	Experimental	2	Python
56	KazKozDev/system-prompt-benchmark Test your LLM system prompts against 287 real-world attack vectors including...	24	Experimental	11	Python
57	liangzid/PromptExtractionEval Source code of the paper "Why Are My Prompts Leaked? Unraveling Prompt...	23	Experimental	7	Python
58	LoonMORTI/promptshield 🛡️ Protect LLM applications with PromptShields, a robust security framework...	23	Experimental	—	Python
59	Eulex0x/cleanmyprompt A transparent, local-only tool to sanitize sensitive info for AI.	23	Experimental	2	HTML
60	Sushegaad/Semantic-Privacy-Guard Semantic Privacy Guard: A Java middleware that intercepts text, identifies...	22	Experimental	1	HTML
61	yangyihe0305-droid/llm-red-team-research Systematic exploration of LLM alignment boundaries through logical stress testing	22	Experimental	1	Shell
62	TechJackSolutions/GAIO Open-source guardrail standard for reducing AI fabrication and improving...	22	Experimental	1	HTML
63	deepanshu-maliyan/guardrails-for-ai-coders Security prompts and checklists for AI coding assistants. One command...	22	Experimental	1	PowerShell
64	AraLeo5/Semantic-Privacy-Guard Identify and protect personal data in text by intercepting and masking PII...	22	Experimental	—	HTML
65	Ethan-YS/PromptGuard-for-Agents 🛡️ Universal AI defense framework protecting agents from prompt injection...	22	Experimental	1	Python
66	tamadip007/getSPNless 🔍 Obtain Kerberos service tickets effortlessly using the SPN-less technique...	21	Experimental	—	Python
67	ianreboot/safeprompt Protect AI automations from prompt injection attacks. One API call stops...	21	Experimental	—	TypeScript
68	sruzima/safe-gamer-helper-chatbot System prompt for SafeGamer Helper, an AI chatbot that teaches kids online...	21	Experimental	—	—
69	ajaakevin/HACKME Explore and analyze WhatsApp data using open-source OSINT tools designed for...	21	Experimental	—	Python
70	anuraag-khare/prompt-fence A Python SDK (backed by Rust) for establishing cryptographic security...	21	Experimental	—	Python
71	Georgeyoussef066/promptshield 🛡️ Secure your LLM applications with PromptShields, a framework designed for...	21	Experimental	—	Python
72	SafellmHub/hguard-go Guardrails for LLMs: detect and block hallucinated tool calls to improve...	21	Experimental	7	Go
73	obscuralabs-AI/Symbolic-Prompt-PenTest Semantic Stealth Attacks & Symbolic Prompt Red Teaming on GPT and other LLMs.	21	Experimental	8	—
74	alexandrughinea/prompt-chainmail-ts Security middleware that shields AI applications from prompt injection,...	20	Experimental	3	TypeScript
75	Pro-GenAI/Smart-Prompt-Eval Evaluating LLM Robustness with Manipulated Prompts	20	Experimental	4	Python
76	bcdannyboy/PromptMatryoshka Multi-Provider LLM Jailbreak Research Framework	20	Experimental	12	Python
77	IAHASH/iahash IA-HASH: A simple, universal way to verify that an AI truly generated a...	20	Experimental	1	Python
78	5ynthaire/5YN-LiveWebpageScanPrecision-Prompt Prompt forces direct, real-time retrieval of unaltered text from URLs with...	20	Experimental	1	—
79	thatgeeman/prompt-injection-cv PoC for prompt injection attacks on LLMs in recruitment. Tests Gemini's...	19	Experimental	2	TeX
80	nodite/llm-guard-ts The Security Toolkit for LLM Interactions (TS version)	17	Experimental	1	—
81	gkanellopoulos/prompthorizon Python library that enables developers to anonymize JSON objects by creating...	17	Experimental	1	Python
82	vladutdinu/prompty-api PromptyAPI, people's LLM-based applications security layer	17	Experimental	1	Python
83	apologetik/CyberPrompts A collection of Large Language Model (LLM) prompts helpful for various...	17	Experimental	—	—
84	fgtrzah/llmrfcpoc combating the llm fomo, feeding the shiny object syndrome, for folly and...	16	Experimental	2	Python
85	valentinaschiavon99/promptguard PromptGuard · LLM Prompt Risk Analyzer · Project for "Neuere Methoden in der...	15	Experimental	—	HTML
86	thepratikguptaa/prompt-injection This repository serves as a comprehensive resource for understanding and...	14	Experimental	1	Python
87	pastsafe-ext/pastesafe Chrome extension that prevents leaking API keys and sensitive data into AI chats	14	Experimental	—	HTML
88	ndpvt-web/aristotelian-compliance-test When Aristotle gets a LinkedIn account and starts red-teaming LLMs....	14	Experimental	—	—
89	yeraydoblasbueno/llm-security-framework Testing LLM vulnerabilities (Jailbreaks, Prompt Injections) locally using...	14	Experimental	—	Jupyter Notebook
90	Tarunjit45/PromptGuard PromptGuard is a pragmatic, opinionated framework for establishing...	14	Experimental	1	Python
91	PMQ9/Ordo-Maledictum-Promptorum Researching a system for preventing prompt injection by separating user...	13	Experimental	—	Rust
92	sachnaror/prompt-guardrails-engine Production-grade FastAPI microservice that forces LLMs to behave....	13	Experimental	—	Python
93	Kimosabey/sentinel-layer AI Safety, Governance, and Security Layer featuring advanced Prompt...	13	Experimental	—	—
94	coollane925/AI-FUNDAMENTALS-AND-PROBING This is a beginner-intermediate level report for people who are interested...	13	Experimental	—	—
95	jyotisin/secure-llm-gateway Secure large language model access by enforcing role-based controls,...	13	Experimental	—	—
96	yogeshwankhede007/WebSec-AI WebSec-AI: A toolkit that combines AI and cybersecurity techniques to detect...	13	Experimental	—	Python
97	seamus-brady/promptbouncer A prototype defense against prompt-based attacks with real-time threat assessment.	13	Experimental	—	Python
98	best247team1-cloud/Ai-shield-pro AI Shield Pro: A secure privacy tool to redact sensitive data and engineer...	13	Experimental	—	HTML
99	SolsticeMoon/Spectre_Steganography_System An experiment in LLM-Assisted steganography using zero-width text.	13	Experimental	—	—
100	rahultrivedi106/Adversarial-Prompt-Vaccination Concept demonstration of Adversarial Prompt Vaccination (APV) — a...	12	Experimental	1	Python
101	RainMaker1707/C2FrameworkDetector Code parts for the proof of concept of "Detection of C2 Frameworks by LLMs...	11	Experimental	—	Python
102	genia-dev/vibraniumdome-docs LLM Security Platform Docs	10	Experimental	2	MDX

Comparisons in this category

llm-guard and SemanticShield (65 vs 41)