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.
Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net
Free OpenClaw security scanner. 3,000+ agents audited. 3-Layer Audit Protocol. OWASP ASI 10/10 coverage. AI agent integrity layer.
Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.
little-canary is a prompt-injection detector that reads attacks by their effect on a sacrificial canary model before they reach production. Puts a small canary model in front of your app, watches whether untrusted input compromises it, and returns block, flag, or pass as an inbound preflight check before your primary model acts.
LLM prompt injection detection for Go applications
Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.
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.
High-performance MCP server for USPTO Enriched Citation API v3 with AI-powered data extraction, token-saving context reduction, progressive disclosure workflows, and seamless cross-MCP integration
Pure-Rust prompt-injection detector with 1.5MB embedded MLP classifier. 98.40% accuracy, p50 14ms CPU inference, bindings for Python/JS/Go. Apache-2.0/MIT alternative to Rebuff (archived) and Lakera Guard.
MCP server for validating legal citations against CourtListener's 9M+ opinion database — detects AI-hallucinated citations, name mismatches, and ambiguous reporters with an interactive citation panel.
A multi-layered prompt injection detection system built with Laravel.
BonkLM - LLM Security Guardrails with Interactive Setup Wizard
High-performance MCP server for USPTO Final Petition Decisions API with context reduction and cross-MCP integration
Antigravity. Claude-code. 🇬🇧 Zero-dependency Node.js CLI to statically audit third-party AI Skills for malicious code patterns before local execution. | 🇪🇸 CLI Node.js sin dependencias para auditar estáticamente Skills de IA buscando código malicioso antes de ejecutarlos.
High-performance MCP server for USPTO Patent Trial and Appeal Board (PTAB) with context reduction, progressive disclosure workflows, and seamless cross-MCP integration
High-performance MCP server for USPTO Patent File Wrapper API with secure document downloads, metadata access, and context reduction
Infrastructure for capturing LLM activations and SAE (Sparse Autoencoders) features, training probes for prompt maliciousness detection, and evaluating out-of-distribution generalization with Leave-One-Dataset-Out (LODO)
An OpenAI-compatible reverse proxy you run yourself. It gives you the features of an AI gateway (guardrails, budgets, rate limits, multi-provider routing) but under your control from your client.
Sunglasses for AI agents. Protection layer + neighborhood watch.
Add a description, image, and links to the prompt-injection-detection topic page so that developers can more easily learn about it.
To associate your repository with the prompt-injection-detection topic, visit your repo's landing page and select "manage topics."