Search
Llmtrace
epappas
Zero-code LLM security & observability proxy. Real-time prompt injection detection, PII scanning, and cost control for OpenAI-compatible APIs. Built in Rust.
...more@openguardrails/moltguard
thomaslwang
AI agent security plugin for OpenClaw: prompt injection detection, PII sanitization, and monitoring dashboard
eslint-plugin-mcp-sdk-security
Ofri Peretz
ESLint plugin for Model Context Protocol (MCP) SDK security — catches tools registered without an input schema, so handlers never run on unvalidated client-supplied arguments.
...morecrypto-randomizer
irfanray
Cryptographically secure random string/number generator using Node.js built-in crypto module. Replaces Math.random() with a bias-free, enterprise-grade solution.
...more@agentic-security-mcp/agent-firewall
shashank022
Agent Firewall for AI and MCP tool calls: deterministic allow, ask, deny permissions with human approval and audit hooks.
...more@yottameta/yotta-security-testing
GitHub Actions
YuanCe (元测) — a disciplined, authorization-first AI security-testing methodology: a four-stage (recon → discovery → verification → reporting) web security testing workflow on authorized targets (self-owned assets / SRC bug bounty / CTF / local labs), with
...morehandoffprobe
heaviside
Adversarial security testing for AI agent handoffs
strict-transport-security
samuelerdtman
Middleware to add Strict-Transport-Security header.
farrow-helmet
aisonren
Security middleware for Farrow HTTP applications that helps secure your web apps by setting various HTTP security headers
...moremiii-security
maruakshay4
Security-focused `SKILL.md` packs for reviewing and hardening LLM systems.
ultra-db.js
iipilix
UltraDB - AdvancedBSON Database Managment System, High-Speed, Ultra Security, Multi Functionalty, and EasyToUse!
secure-storage-ts
madebyraymond
A framework-agnostic secure storage utility for encrypting, securely storing and retrieving app browser storage
mcps-secure
CyberSecAI Ltd
MCPS -- MCP Secure. Cryptographic identity, message signing, and trust verification for the Model Context Protocol.
nulvec
Nulvec
Agent supply chain security — scan packages, code, images, PDFs, and MCP payloads for adversarial attacks
memgar
AI agent memory security — detect, quarantine, and block memory-poisoning attacks (OWASP ASI06) before they reach an LLM agent
...more@neabyte/secure-jwt
neabyte
A secure JWT library with multiple encryption algorithms, zero dependencies, and built-in security for Node.js applications.
...morellm-safe-haven
Vitalik
Harden your AI coding agent in 60 seconds. Security hooks, audit logging, and posture scoring for Claude Code, Cursor, Windsurf, and more.
...moreaidefence
ruvnet
AI Defense System - Production-ready security middleware for protecting AI applications from prompt injection, manipulation attacks, and adversarial inputs. Available as both 'aidefence' (British) and 'aidefense' (American).
...moreKryon
skyvanguard
Autonomous offensive-security agent: recon, authorized pentest, vuln hunting, DFIR & multi-framework compliance from a single prompt. Local-first (llama.cpp), skill-based, deterministic-first.
...moreAgentHound
adithyan-ak
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
...more