#agent-security

Agentlock

An adversarially benchmarked reference implementation for pre-action agent authorization. Framework-agnostic tool permissions, identity veri...

Awesome Agent Skills Security

🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and sk...

Cupcake

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

Trustabl

Static analyzer for agent reliability.

MCP Core Defense

7-phase security proxy for MCP agents. Defends against tool poisoning, description-code inconsistencies, path traversal, and authentication...

Signet

Proof layer for AI agents. Cryptographically verify every action.

7h3 Protocol

Per-message signing + replay protection for MCP and A2A traffic. TypeScript / Python / Rust. Wire version aip/0.1.

Golf Scanner

Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more

Dcp

Permission layer for AI agents — wallet signing, vault access, budgets, and human approvals.

Vaara

Open-source evidence layer for AI governance. Gates every AI agent tool call against your policy and writes a hash-chained execution record...

MCP Gateway

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

Rampart

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do...