Prompt Injection Defense Python Packages

arcjet

Arcjet Python SDK. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks.

ai-prompt-sanitizer

Privacy-first prompt sanitization. Fully local. Zero cloud calls. Fast, smart, and built for real-world AI workflows.

langguard

LangGuard Python Library

decoyshield

Counter-recon honeypot against agentic LLM attackers (PentestGPT/AutoGPT/LangChain). Six deploy modes: Flask drop-in, WSGI/ASGI middleware (Django/FastAPI), callable Python primitives, decoyshield CLI, edge configs (nginx/Caddy/Cloudflare), and Node.js npm package (Express/Fastify). Invisible-to-human, visible-to-LLM bait halts AI scans.

buzur

AI prompt injection defense scanner for agents. 25 phases covering HTML obfuscation, encoding attacks, semantic similarity, behavioral anomaly detection, multi-step attack chains, and more.

aisg

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

capability-reasoning-kernel

Make prompt injection structurally unable to cause an unauthorized effect — a Python reference implementation of the Reasoning Kernel (CaMeL-like) pattern.

promptscreen

Protect your LLMs from prompt injection and jailbreak attacks. Easy-to-use Python package with multiple detection methods, CLI tool, and FastAPI integration.

trust-gate-mcp

MCP server for Trust Gate — policy-gated AI agent decisions with hybrid Ed25519 + ML-DSA-65 (NIST FIPS 204) cryptographic receipts. First post-quantum MCP server.

agent-trap

Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.