agent-security

Star

Here are 15 public repositories matching this topic...

Language:All

Filter by language

All15 Python5 JavaScript2 C++1 Go1 Rust1 TeX1 TypeScript1

Sort:Most stars

Sort options

Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

msoedov /agentic_security

Star1.7k

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

agent-framework ai-red-team prompt-testing llm-security llm-vulnerabilities llm-evaluation llm-fuzzing llm-evaluation-framework llm-guardrails llm-scanner llm-jailbreaks llm-fuzzer llm-fuzzer-aggregator agent-security

UpdatedNov 27, 2025
Python

matank001 /cursor-security-rules

Star334

This repository contains Cursor Security Rules designed to improve the security of both development workflows and AI agent usage within the Cursor environment. These rules aim to enforce safe coding practices, control sensitive operations, and reduce risk in AI-assisted development.

security ai cursor agents aiagents cursorrules agent-security cursor-rules cursor-security

UpdatedAug 27, 2025

lasso-security /mcp-gateway

Star314

A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.

python agent proxy mcp gateway generative-ai gen-ai genai genai-security mcp-server mcp-client agent-security mcp-security

UpdatedJul 15, 2025
Python

fiddlecube /compliant-llm

Star153

Build Secure and Compliant AI agents and MCP Servers. YC W23

mcp ai-agents ai-security ai-compliance mcp-server agent-security mcp-gateway mcp-security

UpdatedJun 6, 2025
Python

eqtylab /cupcake

Star44

Release: Dec 2025. Cupcake makes sure agents follow the rules.

hooks mcp opencode cursor coding-agents gemini-cli agent-security claude-code factory-ai claude-code-sdk

UpdatedNov 28, 2025
Rust

GopherSecurity /gopher-mcp

Star39

MCP C++ SDK - Model Context Protocol implementation in CPP with enterprise-grade security, visibility and connectivity.

python c-plus-plus typescript sdk ai cpp mcp ai-security llm prompt-injection llm-security model-context-protocol agent-security mcp-security model-security

UpdatedNov 28, 2025
C++

aporthq /aport-integrations

Star5

🛡️ Community-built integrations, SDKs, and tools for APort - the neutral trust rail for AI agents. Join Hacktoberfest 2025!

nodejs middleware integrations django express sdk ai stripe nextjs openapi shopify hacktoberfest ai-agents policy-enforcement fastapi hacktoberfest-accepted langchain crewai agent-identity agent-security

UpdatedOct 8, 2025
JavaScript

Defenter-AI /defenter-proxy

Star3

Real-time semantic security for AI coding agents and MCP tools.

security ai-agents ai-security coding-agents agent-security mcp-security

UpdatedNov 24, 2025
Python

pemdes174 /cursor-rules

Star3

🚀 Streamline your Next.js development with practical rules and tested patterns for efficient coding and minimal bugs.

dart agent security awesome ai celery flutter copilot agents intellij-idea cursor-ai-editor windsurf-ai agent-security cursor-rules cursor-rules-java claudecode junie cursor-agent

UpdatedNov 29, 2025

Siddhant-K-code /a2as-implementation-poc

Sponsor

Star2

POC for A2AS.org: Standard for Agentic AI Security

poc a2a agent-security a2a-security a2as implementation-of-paper

UpdatedOct 5, 2025
TypeScript

opena2a-org /agent-identity-management

Star2

Agent Identity Management (AIM) - Security management for autonomous AI agents and MCP servers

cryptography ed25519 identity-management ai-agents mcp-servers agent-security agent-identity-management

UpdatedNov 28, 2025
Go

yusufarbc /mcp-agentic-security-review

Star1

Security analysis of MCP ecosystem – threats, defenses, benchmarks, and agent interoperability.

benchmarking mcp interoperability cybersecurity sandboxing threat-modeling protocol-security supply-chain-security llm-agents agent-security

UpdatedNov 25, 2025
TeX

aicubetechnology /aicube_secure_ai_messaging_framework

Star0

This framework enables secure, decentralized communication between AI agents using blockchain technology and smart contracts. It ensures the integrity, confidentiality, and verifiability of interactions through cryptographic identities, end-to-end encryption, and immutable audit trails.

agent agent-communication agent-collaboration agent-security