 |
VOOZH | about |
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.
Free OpenClaw security scanner. 2,890+ agents audited. 3-Layer Audit Protocol. OWASP ASI 10/10 coverage. AI agent integrity layer.
LLM prompt injection detection for Go applications
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
BonkLM - LLM Security Guardrails with Interactive Setup Wizard
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 Final Petition Decisions API with context reduction and cross-MCP integration
A multi-layered prompt injection detection system built with Laravel.
High-performance MCP server for USPTO Patent File Wrapper API with secure document downloads, metadata access, and context reduction
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.
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.
Official JavaScript/TypeScript SDK for LockLLM
Anticipator is an open-source threat detection platform for multi-agent AI systems.
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.
Enforce security guardrails for large language models in Node.js applications to manage risks and maintain safe usage across platforms and providers.
This repository is meant to be an inspiration and rapid-start workspace for building apps quickly. It combines experiments, starter flows, and reusable tooling in one growing repo so ideas can move into working prototypes with minimal setup.
MalPromptSentinel (MPS) is a Claude Code skill that detects malicious prompts in uploaded files before Claude processes them. It provides two-tier scanning to identify prompt injection attacks, role manipulation attempts, privilege escalation, and other adversarial techniques.
Generic MCP server for Pinecone Assistant API with AI-powered RAG, strategic multi-search, YAML-configurable domains, token optimization, and cross-MCP integration. Reference implementation: USPTO patent examination (MPEP)
Official Python SDK for LockLLM
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."