nono
agent runtime security - zero trust, zero setup, zero latency agent sandboxing
- 5.1k
- Rust
- Apache-2.0
- 2 d ago
agent runtime security - zero trust, zero setup, zero latency agent sandboxing
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.
Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.
Manage secure microVMs — one command from zero to secure sessions, locally and remotely.
Text classification model, used with transformers.
Open-source AI security tool to scan and fix vulnerabilities in your vibe-coded projects before you ship. AXguard by AwareXone.
25 production-tested defensive security skills for Claude Code - WordPress, VPS, Cloudflare, Next.js hardening, AI agent guardrails, MCP security, prompt injection defense, OWASP LLM Top 10, LLM coding failure modes (slopsquatting, hallucinated APIs, sycophancy), incident response, GDPR/DACH compliance. MIT, battle-tested.
Text classification model, used with transformers.
Guides for connecting tool-capable Muapi-hosted models to OpenClaw, Hermes Agent, and other general-purpose AI agents.
Static security scanner for MCP servers, agent skills & plugins: 17 attack patterns / 60 regex signatures, calibrated to a 1% false-positive rate over 196 public MCP servers. In the official MCP Registry: io.github.eltociear/skill-audit-mcp. Also a pay-per-call x402 API.
MCP server that gives AI agents fast, offline full-text search and section-level retrieval over the HackTricks offensive-security wiki.
Text classification model, used with transformers.
Semantic-layer prompt injection defence that separates untrusted instructions from authority while preserving the legitimate task.
🛡️ Zero-dependency invisible prompt injection & ASCII smuggling firewall for LLMs, RAG & AI Agents. Detect, decode, and neutralize hidden Unicode payloads.
Open, reproducible fixture benchmark data and tooling for HOL Guard
Claude Code plugin: warns once per session when a tool payload is about to launch another browser (Chrome/Playwright/Puppeteer/CDP) or fan work out in parallel. Never blocks.
DevContainer features by HOL — AI agent security for VS Code, Codespaces, and remote dev environments