jailbreak-detection repositories

Trending repositories tagged jailbreak-detection, ranked by trending score. Updated daily.

  1. 1
    stylusnexus/agent-armor

    Open-source agent security framework. Detects and defends against AI Agent Traps — content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more. Based on the DeepMind Agent Traps taxonomy.

    GitHub · TypeScript · 7 stars · 0 forks · +2 stars in 24 hours · Trending score 0.82

  2. 2
    Ostorlab/rasp

    Runtime application self-protection (RASP) for Android and iOS apps. Protects a built APK,AAB or IPA without source code changes.

    GitHub · C++ · 7 stars · 2 forks · +2 stars in 24 hours · Trending score 0.61

  3. 3
    hermes-labs-ai/little-canary

    Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

    GitHub · Python · 42 stars · 9 forks · +1 stars in 24 hours · Trending score 0.47

  4. 4
    qusamulab/kagura

    LLVM pass plugin for native code obfuscation and anti-tamper. CFG flattening, string encryption, VM virtualization, anti-cheat, and more. iOS · Android · macOS · Windows · Wasm.

    GitHub · C++ · 50 stars · 11 forks · 0 stars in 24 hours · Trending score 0.46

  5. 5
    DmitrL-dev/AISecurity

    Free, open tools to learn how AI apps get attacked, test a guard on your own data and check what a security test result can prove. EN/RU academy, Guard Lab, eval-bounds. Live protection: spectorn.ai

    GitHub · Go · 113 stars · 19 forks · 0 stars in 24 hours · Trending score 0.41

  6. 6
    guard-spec/guard-spec

    Self-hosted prompt-injection firewall for LLM apps. OpenAI-compatible gateway with rules, an ONNX classifier and embeddings, output guard, alerts, SSO. English and Vietnamese.

    GitHub · Go · 18 stars · 0 forks · 0 stars in 24 hours · Trending score 0.37

  7. 7
    tjcrims0nx/OpenMind-Jailbreak-Lab

    Open-source AI security research lab for reproducible adversarial testing, jailbreak resistance evaluation, and LLM guardrail validation across multiple model providers.

    GitHub · Python · 42 stars · 5 forks · 0 stars in 24 hours · Trending score 0.10

  8. 8
    bastion-soft/pi-detector-bench

    Open, model-agnostic benchmark for prompt-injection detectors — scored on both axes (attack catch-rate and false positives on real traffic), threshold-agnostic, and reproducible from raw scores.

    GitHub · Python · 10 stars · 2 forks · 0 stars in 24 hours · Trending score 0.09

  9. 9
    cgrtml/reasongate

    Explainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.

    GitHub · Python · 17 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08

  10. 10
    jjolano/shadow

    A jailbreak detection bypass for modern iOS jailbreaks.

    GitHub · Logos · 1,102 stars · 193 forks · 0 stars in 24 hours · Trending score 0.01

  11. 11
    Inforaam/MobShield-iOS

    Adaptive, modular RASP for iOS: tunable threat scoring for jailbreak, hooks, debuggers and tampering. No telemetry.

    GitHub · Swift · 11 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    securelayer7/PROMPTPurify

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

    GitHub · TypeScript · 80 stars · 21 forks · 0 stars in 24 hours · Trending score 0.00

  13. 13
    alpkeskin/jev-guardrail

    LLM-agnostic AI guardrail API with Jev. Checks prompts and responses against YAML policies and returns PASSED, BLOCKED or FAILED. Sits between your app and any LLM provider.

    GitHub · Go · 6 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00