Search

Adversarial LLM proxy for testing whether agent security is structural or behavioral

Open source CLI that audits AI agents for security, performance, and model fit

Reins — runtime security and policy enforcement for Claude Code, OpenClaw, and other AI agents.

Security scanner for Agent Skills packages - Detects prompt injection, data exfiltration, and malicious code

Highly isolated Linux container environments optimized specifically for mcp-servers. Secure AI agent tool execution.

Lightweight runtime security agent for AI-powered apps - detects anomalies, blocks attacks, and provides real-time protection

AI coding agent security for Claude Code: reports risky actions in its transcripts, finds secrets left in them, and scores agent credentials.

AI-powered security scanner with 15 scan phases, 10 specialist agents, container/IaC/DAST/taint analysis, and AI-assisted remediation.

Security runtime for AI coding agents: bounded authority, exact-candidate evidence, separate review and human gates. Works with Codex, Claude and OpenCode.

A harness that lets any strong coding model work like a security researcher — narrow scoping, adversarial cross-model review, capability-split tools, parallel hunt + dedupe.

Security scanner and introspection tool for MCP servers. Connect, inspect, detect injection patterns, find tool shadowing, baseline for drift. Single binary, zero dependencies, Go stdlib only.

Lightweight Fast Pre-Audit Security Scanner & Agent Skill for MCP Servers, Agent Hooks, and Firebase Security Rules

MCP server that gives local LLMs (LM Studio, Ollama) live web access plus recon, OSINT, and authorized security-testing tools like Burp/ZAP/Wapiti integration, APK triage, and self-extending skills, all safety-gated by default.

Soter is a safety layer for AI chatbots, agents, RAG systems, and LLM applications.

Open detection rules for AI agent threats. Like Sigma, but for prompt injection, tool poisoning, and agent manipulation.

Zero-dependency MCP gateway: 16 deterministic gates, budget escrow with clawback, Ed25519-signed approvals, hash-chained audit. Governance for AI agents that touch money.

Native high-performance AI agent governance proxy binary

Drop-in prompt injection defense for LLM apps and AI agents — detect, block, and audit injection attacks in real time

LangChain integration for SafePrompt — prompt-injection detection as a callback handler. Validates every prompt flowing through a chain before it reaches the LLM.

A zero-trust encrypted transport layer for AI agents and tools, with AES-GCM encryption, HMAC signing, and identity-aware JSON-RPC messaging.