prompt-injection-detection repositories

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

  1. 1
    cyb3rmik3/prompt-injection-email-samples

    Open test set of .eml emails for checking how email security controls and AI mailbox assistants handle indirect prompt injection. It crosses three intents (system-prompt disclosure, data exfiltration, tool discovery) with three delivery methods (plaintext, hidden HTML, Base64), plus a benign control. All content is fictional and non-routable.

    GitHub · Python · 24 stars · 1 forks · +7 stars in 24 hours · Trending score 1.39

  2. 2
    StackOneHQ/defender

    Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.

    GitHub · TypeScript · 137 stars · 14 forks · 0 stars in 24 hours · Trending score 0.83

  3. 3
    occludra/gateway

    Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

    GitHub · Python · 52 stars · 5 forks · 0 stars in 24 hours · Trending score 0.81

  4. 4
    arcjet/arcjet-js

    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.

    GitHub · TypeScript · 701 stars · 34 forks · 0 stars in 24 hours · Trending score 0.58

  5. 5
    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

  6. 6
    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

  7. 7
    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

  8. 8
    tg-mitra/prompt-injection-detector

    Lightweight prompt injection detector for LLM, RAG and AI agent applications using Sentence Transformers + scikit-learn.

    GitHub · Python · 6 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00