#Prompt-injection
Showing 60 of 89 repositories tagged #prompt-injection, ranked by stars
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.
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.
The Security Toolkit for LLM Interactions
LLM Prompt Injection Detector
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.
a security scanner for custom LLM applications
๐ LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). ๐ Extracts signals from prompts & responses, ensuring safety & security. ๐ก๏ธ Features include text quality, relevance metrics, & sentiment analysis. ๐ A comprehensive tool for LLM observability. ๐
This is a repository that aims to provide updates on the status of jailbreaking the OpenAI GPT language model.
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.
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.
Every practical and proposed defense against prompt injection.
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.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Deterministic safety solutions for probabilistic AI agents
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/
This repository provides a benchmark for prompt injection attacks and defenses in LLMs
prompt attack-defense, prompt Injection, reverse engineering notes and examples | ๆ็คบ่ฏๅฏนๆใ็ ด่งฃไพๅญไธ็ฌ่ฎฐ
Bypass restricted and censored content on AI chat prompts ๐
Prompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3 Prompts.
This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking course.
Runtime security for Agents. Blocks dangerous commands, prevent secret leaks, stop prompt injection, gate risky package installs and visibility and control over tool calls.
Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
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.
Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks
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.
ไป 165 ไธช้กถ็บง AI ไบงๅ็ณป็ปๆ็คบ่ฏไธญ่ธ้ฆๅบ็ 15 ไธชๅฏๆง่ก Agent skill
AspGoat is an intentionally vulnerable ASP.NET Core application for learning and practicing web application security.
AI Security Platform: Defense (61 Rust engines + Micro-Model Swarm) + Offense (39K+ payloads)
The antivirus for OpenClaw โ approve dangerous actions, scan skills, block secret leaks, and keep humans in control, for safety.
๐ค 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
The open source security engine for AI agent and supply-chain trust.
Open-core AI red teaming and offensive AI security evaluation platform.
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.
Code scanner to check for issues in prompts and LLM calls
๐ 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
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.
Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net
My solutions for Lakera's Gandalf
A prompt injection game to collect data for robust ML research
RAG/LLM Security Scanner identifies critical vulnerabilities in AI-powered applications, including chatbots, virtual assistants, and knowledge retrieval systems.
OWASP Foundation web repository
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.
Real-time security for AI agents on Moltbook
Utterly unelegant prompts for local LLMs, with scary results.
A living map of the AI agent security ecosystem.
Spell whisperer is a prompt injection challenges platform based on Grok API.
Zero-code LLM security & observability proxy. Real-time prompt injection detection, PII scanning, and cost control for OpenAI-compatible APIs. Built in Rust.
A repo for all the jailbreaks
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).
Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent ้ๆบๅฎๅ จๅนณๅฐ -- ๅฎ่ฃๅๅฏฉ่จ skillใ24/7 ๅณๆ็ฃๆงใ็คพ็พคๅ ฑไบซๅจ่ ๆ ๅ ฑใ
Open-source AI agent red-team engine, SDK, and CLI. Run offline or against the Humanbound Platform.
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. ๐
Build production ready apps for GPT using Node.js & TypeScript
Whispers in the Machine: Confidentiality in Agentic Systems
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.
AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks
The open-source agent firewall. Prevent AI agents from leaking data, using dangerous tools, and importing poisoned dependencies.
Fast local Rust scanner for AI-agent prompt injection, credential leaks, exfiltration, and risky tool calls
Short list of indirect prompt injection attacks for OpenAI-based models.
A diagnostic methodology for bypassing LLM defense layers โ from input filters to persistent memory exploitation.