#ai-security

Pre-flight risk linting for MCP and agent tools — check the blast radius before your agent runs them.

High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.

AI-powered triage for SAST findings.

Security scanner for AI agent skills and MCP servers. Detects secrets, CVEs, supply chain attacks, and prompt injection in SKILL.md files before they're installed. Pre-install gate for Claude Code, OpenClaw, PicoClaw, NanoBot, FamClaw, and CI/CD pipelines. Single Go binary, MIT licensed.

Provenance-aware memory for AI agents.

Python SDK for Silmaril Firewall prompt injection and jailbreak detection

Agentic Dome

One gateway in front of every MCP server your agents can reach. A server that changes after you approved it is caught, the call is blocked before it runs, and nothing leaves your machine.

该仓库未发布描述。

NSAuditor AI — Open-source, AI-powered network security scanner. 27 plugins, CVE matching, MITRE ATT&CK mapping, verified vulnerabilities, continuous monitoring, MCP integration. Zero data exfiltration. MIT licensed.

AI security gateway that inspects every prompt and response through a multi-layer detection pipeline - enforcing ALLOW, BLOCK, or SANITIZE before anything reaches the model.

AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴露面。

Open-source DevSecOps gateway for AI traffic. Intercept, audit, and route LLM requests to prevent data leaks and enforce zero-trust security policies.

Know what you're letting in — scans, signs and verifies what an agent loads. Agent Skills vs the OWASP Agentic Skills Top 10, with SARIF output and a load-time gate.

Security AI trainer/tuner and research toolkit. Fine-tune LLMs on MITRE ATT&CK-grounded data (QLoRA, GaLore, DeepSpeed, FP8, BitNet). 24K+ training pairs, 18 sources, 100% per-record provenance. Inversion-audit harness (Carlini 2021, 2022; MUSE 2024; LiRA). Terminal GUI for SSH use. 368+ tests.

23-tool MCP server for CVE & vulnerability intelligence. NVD, EPSS, CISA KEV, GitHub Advisory, OSV — unified in one server. Risk scoring, bulk triage, exploit search. 2 dependencies, runs with npx.

TypeScript SDK for Declaw — security-first sandboxing for AI agents

Nation-state grade, defense-in-depth security testing framework. Tests web apps, extensions, desktop, mobile, cloud, AI/LLM, hardware, and supply chain from a single CLI.

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.