Search
agent-injection-firewall
andremt
Deterministic prompt-injection / poison / tool-poisoning firewall for LLM agents — multilingual, evasion-resistant, zero black-box ML in the hot path. OWASP LLM01 / MITRE ATLAS.
...moremantis-redteam
farhanashrafdev
Open-source CLI toolkit for automated red-teaming of LLM-powered applications
@eigenart/agentshield-mcp
eigenart-dev
MCP server for AgentShield — detect prompt injection, jailbreak, and social-engineering attempts in any text before your agent processes it.
...more@ashborn-sec/core
GitHub Actions
Core event model, session ledger, and detectors for Ashborn
@dj_abstract/agent-firewall
dj_abstract
Runtime defensive middleware for AI agent tool calls. Detects, logs, and blocks suspicious patterns at call time — exfiltration trails, dangerous shell, sensitive path writes, the lethal trifecta in motion.
...moreauto-smart-security
haivinh
Production-ready security middleware for Express / NestJS
@sarthi/the-school
sarthi
Shannon-style AI Agent Curriculum - Self-testing platform with 15 grades from basics to advanced AI pentesting, prompt injection, and jailbreak defense
...morewiki-security-composable
bortseb
Composable security plugin foundation for Federated Wiki
@reclaimprotocol/tls
adiwajshing_reclaim
TLS 1.2/1.3 for any JavaScript Environment
Agentic Security
msoedov
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
Gateway
lasso-security
A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.
parsewall
Parsewall maintainers
Fail-closed document inspection before untrusted files reach an LLM
mcpmap
Static attack surface analyzer for AI agents, MCP servers, and LLM tool definitions.
fullcourtdefense
Full Court Defense
Full Court Defense — real-time AI firewall for chatbots, agents, MCP servers and RAG pipelines. Multi-tier threat detection (regex → ML → semantic → AI judge) under 15ms.
...morecontent-filter
efkan
A simple but powerful content-filter. Also provides protection against NoSQL (like MongoDB) injection attacks on Node.js
@fastify/secure-session
matteo.collina
Create a secure stateless cookie session for Fastify
Agent Bypass
1837620622
AgentBypass — Omni Operator LLM Agent Skill (Cknb): Turn any LLM into RE / Pwn / CTF / Pentest / Protocol / Crypto / Mobile / Forensics operator. 20 modules, zero-dependency, all agents.
...more@hawon/nexus
hawon
The all-in-one AI developer framework — session intelligence, code review, prompt injection defense, infinite memory, self-evolving skills
...moreexpress-passport-security
andy-shea
An opionated library to secure Express apps with Passport
@n8n-dev/n8n-nodes-azure-security
kelvinzero
Azure Security Center API specification for Microsoft.Security resource provider.