Top 23 prompt-injection Open-Source Projects

1. iFixAi

   1 4 23,720 8.8 Python

   Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

   

   Project mention: GitHub AI Repos ประจำสัปดาห์: สัปดาห์ที่ agent มีด่านตรวจของตัวเอง (7 ต.ค. 2026) | dev.to | 2026-10-10

   [1] GitHub Trending, weekly, 2026, https://github.com/trending?since=weekly [2] GitHub Trending, รายภาษา (Go, Python, TypeScript) weekly และ monthly, 2026, https://github.com/trending/go?since=weekly [3] GitHub Ranking AI, Top 100 AI Agents, 2026, https://raw.githubusercontent.com/yuxiaopeng/Github-Ranking-AI/main/Top100/AI%20Agents.md [4] NVIDIA/OpenShell, README, 2026, https://github.com/NVIDIA/OpenShell [5] NVIDIA OpenShell documentation, 2026, https://docs.nvidia.com/openshell/latest/index.html [6] NVIDIA/OpenShell, releases, v0.1.2, 28 กันยายน 2026, https://github.com/NVIDIA/OpenShell/releases [7] ifixai-ai/iFixAi, README, 2026, https://github.com/ifixai-ai/iFixAi [8] mvschwarz/openrig, README, 2026, https://github.com/mvschwarz/openrig [9] mvschwarz/openrig, releases, v0.6.5, 4 ตุลาคม 2026, https://github.com/mvschwarz/openrig/releases [10] cursor/plugins, README, 2026, https://github.com/cursor/plugins [11] anthropics/knowledge-work-plugins, README, 2026, https://github.com/anthropics/knowledge-work-plugins [12] JuliusBrussee/caveman, README, 2026, https://github.com/JuliusBrussee/caveman [13] Adeyemi, M. D., Rossi, R. A., Dernoncourt, F., "CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression", arXiv 2606.24083, 2026, https://arxiv.org/abs/2606.24083 [14] Shiryaev, D., "Does Speaking to Agents Like Cavemen Really Save 65% of Tokens? We Test", JetBrains AI Blog, 2026, https://blog.jetbrains.com/ai/2026/07/speak-to-ai-agents-like-cavemen-tosave-tokens/ [15] headroomlabs-ai/headroom, README, 2026, https://github.com/headroomlabs-ai/headroom [16] VectifyAI/PageIndex, README, 2026, https://github.com/VectifyAI/PageIndex [17] VectifyAI/PageIndex, releases, v0.2.21, 1 ตุลาคม 2026, https://github.com/VectifyAI/PageIndex/releases

2. AppSignal

   www.appsignal.com sponsored

   AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.

   

3. AI-Infra-Guard

   2 3 6,790 9.8 Python

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

   

   Project mention: Black Hat Europe 2025 Arsenal: 8 AI Security Tools Transforming Cybersecurity | dev.to | 2025-11-09

   https://github.com/Tencent/AI-Infra-Guard https://github.com/mandiant/harbinger https://github.com/stratosphereips/MIPSEval https://github.com/ErdemOzgen/RedAiRange https://github.com/ReversecLabs/spikee https://github.com/ThalesGroup/sql-data-guard

4. superagent

   3 2 6,763 7.7 TypeScript

   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. (by superagent-ai)

   

   Project mention: Show HN: Local Privacy Firewall-blocks PII and secrets before ChatGPT sees them | news.ycombinator.com | 2025-12-09

5. ADR

   4 1 1,950 8.7 Python

   ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber. (by uber)

   

   Project mention: Uber open-sourced its security monitoring for Claude Code, Cursor and Codex | news.ycombinator.com | 2026-08-06

6. promptmap

   5 2 1,278 6.6 Python

   a security scanner for custom LLM applications

   

7. langkit

   6 5 993 7.0 Jupyter Notebook

   🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀

   

8. agentdojo

   7 3 897 7.3 Python

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

   

   Project mention: AI agents can't tell who's giving the orders. So I built a tiny gate. | dev.to | 2026-09-23

   So I took 10 free, open-source detectors and ran them against 629 realistic attacks from AgentDojo, a research benchmark from ETH Zurich. Each attack was hidden inside normal-looking tool output, like a bill, an email or a hotel review, exactly the way an agent would see it.

9. SaaSHub

   www.saashub.com sponsored

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

10. HOL Guard

    8 0 850 10.0 Python

    Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

    

11. skylos

    9 7 846 9.8 Python

    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/

    

    Project mention: GitHub Actions Security and GitLab CI Security: Static Analysis for CI/CD | dev.to | 2026-05-12

    pip install "git+https://github.com/duriantaco/skylos.git" skylos . --danger

12. brilliant-CV

    10 1 844 9.3 Typst

    💼 another CV template for your job application, yet powered by Typst and more

    

    Project mention: Brilliant CV: A modern, modular, and feature-rich CV template for Typst | news.ycombinator.com | 2026-01-26

13. prompt-injection-defenses

    11 3 724 6.6

    Every practical and proposed defense against prompt injection.

    

    Project mention: Prompt Injection Defenses | news.ycombinator.com | 2025-12-29

14. arcjet-js

    12 11 689 9.7 TypeScript

    Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.

    

15. Open-Prompt-Injection

    13 1 504 2.8 Python

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

    

16. 0

    14 1 511 9.9 TypeScript

    The multiplayer AI offensive security OS - open, self-improving, extensible. Find, verify, and fix vulnerabilities. (by 0sec-labs)

    

    Project mention: Cybersecurity harness for full-stack LLM-driven penetration testing | news.ycombinator.com | 2026-09-29

17. agent-threat-rules

    15 1 408 9.9 TypeScript

    Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.

    

    Project mention: I Scanned 2,386 MCP Packages on npm. 402 Were Critical. Here's What I Found. | dev.to | 2026-03-22

    Everything is open source (MIT): ATR rules + PanGuard scanner

18. agentseal

    16 2 377 9.2 Python

    Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

    

    Project mention: AgentSeal – Security scanner for AI agents (150 attack probes) | news.ycombinator.com | 2026-03-06

    GitHub: https://github.com/AgentSeal/agentseal

19. aegis

    17 4 269 5.6 Python

    Self-hardening firewall for large language models (by automorphic-ai)

    

20. humanbound

    18 7 192 9.3 Python

    Open-source adversarial testing engine, SDK, and CLI for AI agents. Runs locally or against the Humanbound Platform.

    

    Project mention: Google's Gemini breakout and what Google's own vulnerability data says about agents | dev.to | 2026-10-12

    Humanbound's engine, SDK and CLI are open source (Apache-2.0): star the repo and read the code at https://github.com/humanbound/humanbound. To run adversarial tests against your own agents, sign up for the free Community plan at https://app.humanbound.ai

21. diagnostic

    19 1 160 - Python

    iFixAi. The open-source diagnostic for AI misalignment. 32 tests across fabrication, manipulation, deception, unpredictability, and opacity. Provider-agnostic. Runs against OpenAI, Anthropic, Bedrock, Azure, Gemini, and more. Letter grade in under 5 minutes, content-addressed manifest for bit-identical replay. Built by iMe.

    

    Project mention: Open-source diagnostic for Al misalignment. Model agnostic, industry agnostic | news.ycombinator.com | 2026-05-04

22. LLMSecurityGuide

    20 3 155 6.0

    A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt injection, adversarial attacks, real-world incidents, and practical defenses. Includes catalogs of red-teaming tools, guardrails, and mitigation strategies to help developers, researchers, and security teams deploy AI responsibly.

    

    Project mention: LLM Security Guide – 100 tools and real-world attacks from 370 experts | news.ycombinator.com | 2025-11-03

23. gateway

    21 1 131 7.6 Python

    The Open Source Firewall for LLMs. A self-hosted gateway to secure and control AI applications with powerful guardrails. (by trylonai)

    

24. clawshield-public

    22 1 130 8.1 Go

    Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF kernel monitor. YAML policy engine, audit logging, 5 AI agents with RAG knowledge bases.

    

    Project mention: Show HN: ClawShield – Open-source security proxy for AI agents (Go, eBPF) | news.ycombinator.com | 2026-03-01

25. localmod

    23 1 127 8.5 Python

    Self-hosted content moderation API that outperforms Amazon Comprehend. 100% offline, your data never leaves your server. Text + Image moderation.

    

    Project mention: I Built a Self-Hosted Content Moderation API (Open Source) | dev.to | 2026-01-01

    So I built LocalMod, a fully offline, self-hosted content moderation API. It handles both text and images, and actually outperforms some commercial services on toxicity benchmarks.

26. SaaSHub

    www.saashub.com sponsored

    SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

    

prompt-injection related posts

• AI agents can't tell who's giving the orders. So I built a tiny gate.

  1 project | dev.to | 23 Sep 2026

• Designing an eval harness for prompt-injection detection: what measuring my defenses actually taught me

  4 projects | dev.to | 21 Sep 2026

• AgentGuard Update: Open Core, Break-Glass Governance — and the First Real-World Finds

  3 projects | dev.to | 9 Sep 2026

• Sentinel-scan-CLI – a CLI that runs 15 prompt-injection attacks against your LLM

  1 project | news.ycombinator.com | 25 Aug 2026

• Blocking prompt injection deterministically costs 40% false positives

  1 project | news.ycombinator.com | 17 Aug 2026

• I tested whether agents leak secrets without being asked — and whether my scanner catches it when they do

  1 project | dev.to | 10 Aug 2026

• agent-shield-runtime v0.1.0: hook de despliegue que conecta 5 sensores de defensa de agentes IA

  6 projects | dev.to | 20 Jul 2026
• A note from our sponsor - AppSignal
  www.appsignal.com | 14 Oct 2026

  Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →

Index

Sponsored

AppSignal knows why the f*#k it crashed.

Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.

www.appsignal.com