Havuz

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

Soup Wall: open-source security for AI agents and model traffic. Local Agent, Gateway, self-hosted Console. Apache-2.0.

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a fo

Security-First Agentic IDE Coding Harness

An open library of 206 security skills for AI agents — pentest, bug bounty, CTF, reversing & defense across 23 domains, with CI-verified rou

Runtime security platform for LLM agent tool calls on Kubernetes

Free NVIDIA DLI course: build, coordinate, and secure AI agents with NemoClaw and OpenShell. Browser-based, no GPU required. Available in En

The autonomous pentester that proves its findings — AI-driven, evidence-first, behind-login.

Open-source runtime security and execution control for autonomous AI agents. ALLOW, BLOCK, ESCALATE at the execution boundary with auditable

Recovering verbatim private reasoning from Claude extended-thinking signatures, with a local byte-exact verifier.

Security scanner for AI agent skills. Flags known prompt-injection, data-exfiltration and malicious-payload patterns before you install

Free, local-first academic integrity checker and MCP server: citation hallucination detection, AI-text and plagiarism signals, venue guideli

Trust & security scanner for AI agents and MCP servers — OWASP-mapped findings, Trust Cards (A–F grades), SARIF + CI gate. Free CLI, zero te

Credential isolation for AI agents — stop leaking secrets to your agents. TAP is a credential proxy: agents never see secret values; optiona

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-bound

Open-source adversary emulation for AI agents and MCP servers.

Policy-aware static taint analysis for detecting sensitive-data flows into LLM APIs.

Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Ope

Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: an

Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.

Let your AI agent use your passwords and API keys - without ever letting it see them

Trace-backed Agent Authorization Reviews for tool-using AI agents. Staging-only evidence for payment, record-change, access, and export acti

🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and ve

Executable security regression testing for agentic applications and MCP-integrated systems.

Zero-dependency TypeScript secret and PII redaction for any SDK, logs, HTTP, LLM prompts, and scoped MCP tool boundaries.

Vetix — Automated scanning, identification, and assessment of SKILL security risks, based on Golang.

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

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

Your app is guilty until proven secure: an agent skill whose /hack-me breaks into your own running app, proves each bug with a real request,

The AI security agent guards your code.

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

Find and fix web-app vulnerabilities in one command — SAST + DAST + AI, for devs who aren't security experts.

RAG pipeline security testing toolkit - 27 techniques across 6 kill chain phases, mapped to MITRE ATLAS

Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, ref

Detect and patch vulnerabilities in AI-generated Python code — VS Code extension

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol server

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as str

🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Repro

An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.

Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (RAG

The execution safety layer for AI agents.

AI security agent for the Python supply chain: scans packages, generates exploits, and validates them in Docker, autonomously.

Claude skill that catches hidden prompt-injection text in documents before acting on them

AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.

Governed Postgres access for AI assistants: an MCP gateway with OAuth 2.1 and OIDC login, one Postgres role per person, database-enforced re

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a clien

Scan a codebase for AI SDKs, MCP servers and agent tools; map risks to NIST AI RMF, ISO 42001, EU AI Act and the OWASP LLM and Agentic Top 1

Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial