#ai-security

A runtime for reliable multi-agent systems with durable workflows, resumable execution, and human-in-the-loop control

AI agent security harness, adversarial testing: 623 executable tests in the v4.21.3 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loop, skill supply chain. Four target shapes: a verdict must be able to be wrong AND to be right. OWASP Agentic v1.1 T1-T17, AIUC-1 19/20 (2026-Q1/Q2 set), NIST AI 800-2.

Memory security for AI agents. Scan native memory writes, gate tools on bound hosts, inspect what was stored. Not a second brain.

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.

Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load balancing across OpenAI, Anthropic, Ollama, vLLM, and any compatible backend. Identity-based access, virtual API keys, and end-to-end encryption via OpenZiti

Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。

Prevent accidental PII leakage in LLM prompts before they hit the model.

Local credential control for AI coding agents.

Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.

BonkLM - LLM Security Guardrails with Interactive Setup Wizard

Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.

A Laravel security boundary for AI-triggered application actions. It bounds what an agent may do — authority, duplication, rate, approval — not what it was trying to do.

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.

Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,583 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.

Agentic AI EDR for developer workstations and autonomous agent swarms. Build Swarm Detection & Response platforms with Clawdstrike.

Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-aware, author-independent, and shift-left: secure_prompt secures the prompt before code generation. The security MCP for vibe coding: 450 rules, 39 tools, CLI + doctor for Next.js, Supabase, Clerk, Stripe, Prisma, Hono & MCP.

Static security scanner for AI agents, MCP tools, and LLM applications. Detects OWASP LLM Top 10 risks, unsafe tool use, prompt injection paths, secrets, and AI infrastructure misconfigurations. Zero runtime dependencies.

Native Post-Quantum Agent Messaging Protocol (N-PAMP): A 20 channel, wire binary, streaming protocol for AI Agents with hybrid post-quantum cryptography.

An AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.

Audit your AI agent configs before you run them — prompt injection, rogue MCP servers, credential-exfil. Plus dependency vetting.

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

Local-first trust layer for AI coding agents: structural prompt-injection and action guards, secret scanning, semantic memory, code review, and 17 MCP tools. No model API required.

TypeScript SDK for Silmaril Firewall

OpenAIDR — session collection for AI coding agents. Reads what agents write to disk and normalises it into one session model.

CLI to spot risky AI skill packages before you use them. Scans for injection, exfiltration, supply chain, and other threats.

Open-source agent security framework. Detects and defends against AI Agent Traps — content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more. Based on the DeepMind Agent Traps taxonomy.

Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.