#Prompt-injection

Showing 60 of 89 repositories tagged #prompt-injection, ranked by stars

superagent-ai
superagent-ai
superagent

Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

Score
100
โ˜… 6.7k โ‘‚ 962 +2/day
TypeScript
Tencent
Tencent
AI-Infra-Guard

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

Score
98
โ˜… 4.1k โ‘‚ 393 โ€”
Python
protectai
protectai
llm-guard

The Security Toolkit for LLM Interactions

Score
100
โ˜… 3.2k โ‘‚ 416 +14/day
Python
protectai
protectai
rebuff

LLM Prompt Injection Detector

Score
89
โ˜… 1.5k โ‘‚ 137 +1/day
TypeScript
ifixai-ai
ifixai-ai
iFixAi

Catch your AI's mistakes and blind spots before your customers or regulators do. iFixAi runs 45 inspections, 32 graded core plus 13 extended for frontier risks like sabotage, sandbagging, and oversight evasion. It returns a letter grade in under 5 minutes. Industry and model agnostic.

Score
0
โ˜… 1.3k โ‘‚ 166 +44/day
Python
utkusen
utkusen
promptmap

a security scanner for custom LLM applications

Score
95
โ˜… 1.2k โ‘‚ 127 +4/day
Python
whylabs
whylabs
langkit

๐Ÿ” LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). ๐Ÿ“š Extracts signals from prompts & responses, ensuring safety & security. ๐Ÿ›ก๏ธ Features include text quality, relevance metrics, & sentiment analysis. ๐Ÿ“Š A comprehensive tool for LLM observability. ๐Ÿ‘€

Score
84
โ˜… 992 โ‘‚ 73 โ€”
Jupyter Notebook
tg12
tg12
gpt_jailbreak_status

This is a repository that aims to provide updates on the status of jailbreaking the OpenAI GPT language model.

Score
97
โ˜… 933 โ‘‚ 66 โ€”
HTML
luckyPipewrench
luckyPipewrench
pipelock

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

Score
100
โ˜… 751 โ‘‚ 87 +1/day
Go
toby-bridges
toby-bridges
api-relay-audit

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

Score
100
โ˜… 748 โ‘‚ 72 +10/day
Python
tldrsec
tldrsec
prompt-injection-defenses

Every practical and proposed defense against prompt injection.

Score
59
โ˜… 713 โ‘‚ 57 โ€”
arcjet
arcjet
arcjet-js

Arcjet JavaScript (JS) / TypeScript SDK. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks.

Score
93
โ˜… 672 โ‘‚ 30 โ€”
TypeScript
ethz-spylab
ethz-spylab
agentdojo

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

Score
95
โ˜… 655 โ‘‚ 168 +9/day
Python
SponsioLabs
SponsioLabs
Sponsio

Deterministic safety solutions for probabilistic AI agents

Score
0
โ˜… 466 โ‘‚ 28 +1/day
Python
duriantaco
duriantaco
skylos

Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistakes before merge. For first timers refer to https://duriantaco.github.io/skylos/repo-map/

Score
0
โ˜… 465 โ‘‚ 23 +3/day
Python
liu00222
liu00222
Open-Prompt-Injection

This repository provides a benchmark for prompt injection attacks and defenses in LLMs

Score
92
โ˜… 464 โ‘‚ 73 โ€”
Python
yunwei37
yunwei37
prompt-hacker-collections

prompt attack-defense, prompt Injection, reverse engineering notes and examples | ๆ็คบ่ฏๅฏนๆŠ—ใ€็ ด่งฃไพ‹ๅญไธŽ็ฌ”่ฎฐ

Score
63
โ˜… 336 โ‘‚ 36 +1/day
trinib
trinib
ZORG-Jailbreak-Prompt-Text

Bypass restricted and censored content on AI chat prompts ๐Ÿ˜ˆ

Score
74
โ˜… 287 โ‘‚ 47 +3/day
langgptai
langgptai
Awesome-Multimodal-Prompts

Prompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3 Prompts.

Score
61
โ˜… 286 โ‘‚ 25 โ€”
TrustAI-laboratory
TrustAI-laboratory
Learn-Prompt-Hacking

This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking course.

Score
55
โ˜… 282 โ‘‚ 37 โ€”
Jupyter Notebook
PrismorSec
PrismorSec
prismor

Runtime security for Agents. Blocks dangerous commands, prevent secret leaks, stop prompt injection, gate risky package installs and visibility and control over tool calls.

Score
91
โ˜… 227 โ‘‚ 18 +5/day
Python
SantanderAI
SantanderAI
autoguardrails

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

Score
89
โ˜… 122 โ‘‚ 31 +10/day
Python
jnMetaCode
jnMetaCode
shellward

AI Agent Security Middleware โ€” 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP server for Claude Code, Cursor, LangChain, Hermes Agent & more.

Score
84
โ˜… 122 โ‘‚ 20 +6/day
TypeScript
pasquini-dario
pasquini-dario
project_mantis

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks

Score
14
โ˜… 116 โ‘‚ 13 โ€”
Python
sinewaveai
sinewaveai
agent-security-scanner-mcp

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.

Score
80
โ˜… 112 โ‘‚ 10 +1/day
JavaScript
kangarooking
kangarooking
system-prompt-skills

ไปŽ 165 ไธช้กถ็บง AI ไบงๅ“็ณป็ปŸๆ็คบ่ฏไธญ่’ธ้ฆๅ‡บ็š„ 15 ไธชๅฏๆ‰ง่กŒ Agent skill

Score
87
โ˜… 108 โ‘‚ 29 +8/day
Soham7-dev
Soham7-dev
AspGoat

AspGoat is an intentionally vulnerable ASP.NET Core application for learning and practicing web application security.

Score
61
โ˜… 106 โ‘‚ 91 โ€”
JavaScript
DmitrL-dev
DmitrL-dev
AISecurity

AI Security Platform: Defense (61 Rust engines + Micro-Model Swarm) + Offense (39K+ payloads)

Score
82
โ˜… 105 โ‘‚ 17 โ€”
Python
Gk0Wk
Gk0Wk
ClawGuard

The antivirus for OpenClaw โ€” approve dangerous actions, scan skills, block secret leaks, and keep humans in control, for safety.

Score
57
โ˜… 100 โ‘‚ 2 โ€”
TypeScript
7WaySecurity
7WaySecurity
ai_osint

๐Ÿค– Curated AI OSINT resources โ€” Google dorks, Shodan queries, GitHub dorks, and techniques to discover exposed LLM endpoints, leaked AI API keys, misconfigured vector databases, and unprotected AI agents

Score
77
โ˜… 97 โ‘‚ 13 โ€”
garagon
garagon
aguara

The open source security engine for AI agent and supply-chain trust.

Score
75
โ˜… 85 โ‘‚ 15 โ€”
Go
Aimer-zero
Aimer-zero
redforge-ai

Open-core AI red teaming and offensive AI security evaluation platform.

Score
70
โ˜… 81 โ‘‚ 16 โ€”
Python
arsbr
arsbr
Veritensor

The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data Poisoning, PII, and Prompt Injections. Secure your AI Supply Chain.

Score
82
โ˜… 80 โ‘‚ 6 โ€”
Python
kereva-dev
kereva-dev
kereva-scanner

Code scanner to check for issues in prompts and LLM calls

Score
7
โ˜… 78 โ‘‚ 8 โ€”
Python
RikyZ90
RikyZ90
ShibaClaw

๐Ÿ• Self-hosted security-first AI agent ยท 23 providers ยท 11 chat channels ยท WebUI ยท 3-level memory ยท task-schedule ยท automation ยท skills ยท MCP

Score
64
โ˜… 77 โ‘‚ 8 +3/day
Python
peg
peg
rampart

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

Score
66
โ˜… 76 โ‘‚ 12 +1/day
Go
securelayer7
securelayer7
PROMPTPurify

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net

Score
68
โ˜… 76 โ‘‚ 20 +2/day
TypeScript
ZapDos7
ZapDos7
lakera-gandalf

My solutions for Lakera's Gandalf

Score
37
โ˜… 75 โ‘‚ 14 +1/day
HumanCompatibleAI
HumanCompatibleAI
tensor-trust

A prompt injection game to collect data for robust ML research

Score
5
โ˜… 71 โ‘‚ 9 โ€”
Python
olegnazarov
olegnazarov
rag-security-scanner

RAG/LLM Security Scanner identifies critical vulnerabilities in AI-powered applications, including chatbots, virtual assistants, and knowledge retrieval systems.

Score
18
โ˜… 71 โ‘‚ 10 โ€”
Python
OWASP
OWASP
www-project-agent-memory-guard

OWASP Foundation web repository

Score
73
โ˜… 69 โ‘‚ 21 +6/day
Python
sinanw
sinanw
llm-security-prompt-injection

This project investigates the security of large language models by performing binary classification of a set of input prompts to discover malicious prompts. Several approaches have been analyzed using classical ML algorithms, a trained LLM model, and a fine-tuned LLM model.

Score
2
โ˜… 65 โ‘‚ 13 โ€”
Jupyter Notebook
NirDiamant
NirDiamant
moltbook-agent-guard

Real-time security for AI agents on Moltbook

Score
41
โ˜… 64 โ‘‚ 10 โ€”
Python
davidegat
davidegat
happy-prompts

Utterly unelegant prompts for local LLMs, with scary results.

Score
32
โ˜… 62 โ‘‚ 7 +4/day
ProjectRecon
ProjectRecon
awesome-ai-agents-security

A living map of the AI agent security ecosystem.

Score
86
โ˜… 54 โ‘‚ 60 +3/day
CX330Blake
CX330Blake
Spell-Whisperer

Spell whisperer is a prompt injection challenges platform based on Grok API.

Score
43
โ˜… 54 โ‘‚ 3 โ€”
TypeScript
techlab-innov
techlab-innov
llmtrace

Zero-code LLM security & observability proxy. Real-time prompt injection detection, PII scanning, and cost control for OpenAI-compatible APIs. Built in Rust.

Score
79
โ˜… 54 โ‘‚ 1 โ€”
Python
tuxsharxsec
tuxsharxsec
Jailbreaks

A repo for all the jailbreaks

Score
71
โ˜… 51 โ‘‚ 5 โ€”
Roff
killertcell428
killertcell428
aigis

Deterministic, zero-dependency Python firewall for AI agents โ€” MCP rug-pull, memory poisoning, indirect injection, exfil channels. 44 compliance templates (US/CN/JP/EU).

Score
55
โ˜… 51 โ‘‚ 7 โ€”
Python
panguard-ai
panguard-ai
panguard-ai

Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent ้–‹ๆบๅฎ‰ๅ…จๅนณๅฐ -- ๅฎ‰่ฃๅ‰ๅฏฉ่จˆ skillใ€24/7 ๅณๆ™‚็›ฃๆŽงใ€็คพ็พคๅ…ฑไบซๅจ่„…ๆƒ…ๅ ฑใ€‚

Score
52
โ˜… 51 โ‘‚ 5 +1/day
TypeScript
humanbound
humanbound
humanbound

Open-source AI agent red-team engine, SDK, and CLI. Run offline or against the Humanbound Platform.

Score
50
โ˜… 51 โ‘‚ 5 +6/day
Python
jailbreakme-xyz
jailbreakme-xyz
jailbreak

jailbreakme.xyz is an open-source decentralized app (dApp) where users are challenged to try and jailbreak pre-existing LLMs in order to find weaknesses and be rewarded. ๐Ÿ†

Score
34
โ˜… 49 โ‘‚ 18 โ€”
JavaScript
GPTSafe
GPTSafe
PromptGuard

Build production ready apps for GPT using Node.js & TypeScript

Score
18
โ˜… 48 โ‘‚ 4 โ€”
TypeScript
LostOxygen
LostOxygen
llm-confidentiality

Whispers in the Machine: Confidentiality in Agentic Systems

Score
68
โ˜… 45 โ‘‚ 9 โ€”
Python
MaxMLang
MaxMLang
pytector

Easy to use LLM Prompt Injection Detection and Prompt Input Sanitization / Detector Python Package with support for local models, API-based safeguards, and LangChain guardrails.

Score
76
โ˜… 44 โ‘‚ 24 โ€”
Python
CollieAi
CollieAi
llm-firewall

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

Score
36
โ˜… 43 โ‘‚ 1 โ€”
darfaz
darfaz
clawmoat

The open-source agent firewall. Prevent AI agents from leaking data, using dangerous tools, and importing poisoned dependencies.

Score
45
โ˜… 41 โ‘‚ 6 +1/day
JavaScript
ArmorerLabs
ArmorerLabs
Armorer-Guard

Fast local Rust scanner for AI-agent prompt injection, credential leaks, exfiltration, and risky tool calls

Score
48
โ˜… 40 โ‘‚ 10 โ€”
Rust
grepstrength
grepstrength
WideOpenAI

Short list of indirect prompt injection attacks for OpenAI-based models.

Score
21
โ˜… 39 โ‘‚ 4 โ€”
SnailSploit
SnailSploit
The-LLM-Red-Teamer-s-Playbook

A diagnostic methodology for bypassing LLM defense layers โ€” from input filters to persistent memory exploitation.

Score
66
โ˜… 38 โ‘‚ 7 +2/day
Related Topics
#llm-security#ai-security#llm#security#prompt-engineering#cybersecurity#ai-agents#guardrails#chatgpt#ai-safety#agent-security#python

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly