Search
sentinel-protocol
rtnlabs
The Reference Architecture for Local AI Governance & Firewalling. Secure, deterministic protection for Agents, MCP, and LLMs.
...moreorigin-fortress
origin-fortress
Security moat for AI agents. Runtime protection against prompt injection, tool misuse, and data exfiltration.
sentinelcore-ai
CipherAI
A security control plane for LLM and agent applications: detection, provenance, risk, authorization, policy and enforcement.
...moresentinel-prox
Pali Krishna Harshith
Provenance-aware security proxy for AI agents: block prompt-injection actions at the MCP tool boundary.
mylonite
Open-source framework for AI-layer security testing — finds AI-agent weaknesses and writes the regression tests that close them.
...moreBv Mcp
MadaBurns
Open-source DNS & email security scanner. One MCP endpoint, 57 checks, zero install. Cloudflare Workers.
@cerberus-ai/core
manofstyle04
Agentic AI runtime security platform — detects, correlates, and interrupts the Lethal Trifecta attack pattern across all agentic AI systems.
...moreblackwall-llm-shield-python
Security middleware for Python LLM apps and services. Blocks prompt injection, masks PII, inspects outputs, and gates agent tools.
...moreredcell
Sahil Sadhwani
The MCP security scanner that actively exploits: prove SSRF, path traversal, command injection and more in MCP servers (OWASP MCP Top 10).
...moreHardware Compliance Handbook
Platanor
AI-ready knowledge base of security & compliance regulations for hardware and connected-device manufacturers - structured, indexed, and machine-readable for LLMs and agents.
...moredsh-riskproof
GitHub Actions
Provenance-aware execution security for DeepSeek Harness. Track sensitive data across tool calls and stop risky side effects before execution.
...morellmpromptdefender
llmpromptdefender contributors
Static security scanner for LLM and agentic source code — finds prompt-injection, context-leak, PII, RAG, and agent-tool vulnerabilities before deployment.
...moreTrust Plane
abluva-research
Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.
...moreCybermes
Zyrexnn
Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.
...more@ninjascout77/httptoolkit-mcp
ninjascout777
MCP server for LLM-driven security testing via HTTPToolkit — capture analysis, mutation-based replay, audit trails for mobile and electron app pentesting
...more@wd041216-bit/ironclaw-agent-guard
wd041216-bit
Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.
...more@eigenart/agentshield
eigenart-dev
Six-layer AI agent security for ElizaOS on Solana — prompt injection defense, transaction policies, anomaly detection, and on-chain audit trail. Part of the AgentShield platform (agentshield.pro).
...more@blamejs/exceptd-skills
dotcoocoo
AI security skills grounded in mid-2026 threat reality, not stale framework documentation. 38 skills, 10 catalogs, 34 jurisdictions, pre-computed indexes, Ed25519-signed.
...moreCyvisguard
flankerhqd
Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.
...moreOrchard Kit
OrchardHarmonics
Complete alignment and safety architecture for autonomous AI agents. Membrane security, continuous trust verification, epistemic hygiene, emergence protocols, and defence tools. 30 years of cybernetic research — deployable today.
...more