The fastest Trust Layer for AI Agents
Ultra-fast, low latency LLM prompt injection/jailbreak detection ⛓️
Veil Armor is an enterprise-grade security framework for Large Language Models (LLMs) that provides multi-layered protection against prompt injections, jailbreaks, PII leakage, and sophisticated attack vectors.
A Input Prompt Guard Library with Bert model trained on prompt injection dataset
Security scanners for LLM prompts and responses: prompt injection, PII (incl. Russian documents), secrets, toxicity. Maintained continuation of LLM Guard; runs without PyTorch.
Runtime defense for AI agents. 24 inline defenses, 3 output scanners, MCP server, framework adapters.
Developer-first security layer for AI applications. Deterministic detection of prompt injection across 13 attack categories.
A self-hosted LLM gateway with built-in input/output guardrails — multi-protocol routing, quotas, audit logging, and TOTP-MFA admin console
Example of running last_layer with FastAPI on vercel
LLM Guard - A pure Rust implementation guardrails for LLM input/output.
My container images, built by CI and published to GHCR.
Input-boundary prompt injection detection for LLM applications using Protect AI’s LLM Guard.
Python security gates for LLM systems: prompt-injection filtering, model artifact scanning, and garak-based red-team scoring.
Stop testing your model. Test your guardrail layer. guardrailprobe fires 78 OWASP LLM Top 10 attack probes across 11 backends — Lakera, NeMo, Presidio, Azure Content Safety, Bedrock Guardrails, LLM Guard, and five more — and outputs signed PDF and JSON comparison reports.
One enforcement layer for all your LLM guardrails. Drop in NeMo, Presidio, Lakera, OpenAI Moderation, Azure Content Safety, AWS Bedrock, LlamaFirewall, or LLM Guard — swap backends without touching your app code. Async-native. Covers OWASP LLM Top 10 attack categories.
To associate your repository with the llm-guard topic, visit your repo's landing page and select "manage topics."