agent-security

Tracekit

+204

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

SkillSpector

+2.1k

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

nasiko

+746

The Open Runtime for AI Agents

agent-beacon

+285

The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu

AI-Infra-Guard

+246

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

nolabs-ai/nono

+94

agent runtime security - zero trust, zero setup, zero latency agent sandboxing

guardana

+20

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

SkillEvaluator

+19

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

uber/ADR

+11

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.