Git Stars Git Stars

#agent-security Repositories

Discover 25 active open source GitHub repositories tagged with #agent-security, accumulating 76,391 total stars (averaging 3,055 stars per project). Leading this topic is NVIDIA/SkillSpector with 27,129 stars.

25
Total Repositories
76,391
Total Stars
3,055
Avg Stars/Repo
1
NVIDIA/SkillSpector

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.

NVIDIA
โญ 27,129 Python ๐Ÿ‘ค NVIDIA Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-03-21
2
Nasiko-Labs/nasiko

The Open Runtime for AI Agents

Nasiko-Labs
โญ 11,948 Rust ๐Ÿ‘ค Nasiko-Labs Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-02-12
3
Tencent/AI-Infra-Guard

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

Tencent
โญ 7,604 Python ๐Ÿ‘ค Tencent Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-12-25
4
nolabs-ai/nono

Agent runtime security โ€” zero-trust, zero-setup, zero-latency agent sandboxing

nolabs-ai
โญ 5,060 Rust ๐Ÿ‘ค nolabs-ai Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-01-31
5
NVIDIA/SkillEvaluator

Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.

NVIDIA
โญ 4,300 Python ๐Ÿ‘ค NVIDIA Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-06-24
6
Asymptote-Labs/agent-beacon

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

Asymptote-Labs
โญ 3,584 Go ๐Ÿ‘ค Asymptote-Labs Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-05-12
7
uber/ADR

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

uber
โญ 2,143 Python ๐Ÿ‘ค uber Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-04-19
8
msoedov/agentic_security

Agentic LLM Vulnerability Scanner / AI red teaming kit ๐Ÿงช

msoedov
โญ 2,048 Python ๐Ÿ‘ค msoedov User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2024-04-11
9
perplexityai/numbat

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

perplexityai
โญ 1,177 Go ๐Ÿ‘ค perplexityai Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-07-24
10
hashgraph-online/hol-guard

Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

hashgraph-online
โญ 1,117 Rust ๐Ÿ‘ค hashgraph-online Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-03-28
11
Pantheon-Security/medusa

AI-first security scanner. NEW in v2026.7: Claude Code compromise detection โ€” vet .claude/ hooks, permissions & skills before you clone โ€” plus an always-on AI attack-signature scanner and native Rust & PHP rules. Also: medusa scan --git to vet any repo, medusa secrets scan for leaked API keys. 40,000+ patterns, zero setup.

Pantheon-Security
โญ 1,023 Python ๐Ÿ‘ค Pantheon-Security Organization ๐Ÿ• Updated 2026-08-10 ๐Ÿ“… Created 2025-11-15
12
pipelab-org/pipelock

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

pipelab-org
โญ 1,013 Go ๐Ÿ‘ค pipelab-org Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-08
13
asamassekou10/ship-safe

The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.

asamassekou10
โญ 873 JavaScript ๐Ÿ‘ค asamassekou10 User ๐Ÿ• Updated 2026-10-17 ๐Ÿ“… Created 2026-02-02
14
Cygnux-Labs/Tracekit

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

Cygnux-Labs
โญ 759 Python ๐Ÿ‘ค Cygnux-Labs Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-09-26
15
AgentSafeLabs/safelabs-eval

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01โ€“ASI10 taxonomy

AgentSafeLabs
โญ 713 Python ๐Ÿ‘ค AgentSafeLabs Organization ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2026-05-25
16
arcjet/arcjet-js

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.

arcjet
โญ 700 TypeScript ๐Ÿ‘ค arcjet Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2023-11-30
17
agentic-os-org/ANOLISA

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

agentic-os-org
โญ 686 Rust ๐Ÿ‘ค agentic-os-org Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-03-30
18
solongate/agent-security

Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.

solongate
โญ 674 Go ๐Ÿ‘ค solongate Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-09-27
19
samvallad33/vestige

Deterministic Operating System, Safety Kernel, and Causal Nervous System for AI Agents.

samvallad33
โญ 662 Rust ๐Ÿ‘ค samvallad33 User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-01-25
20
decionis/agent-safe-pipeline

Open-source gateway that puts authorization in front of every action your AI agents, workflows, and pipelines take before it commits: payments, trades, price changes, deployments, and API calls run once on a single-use grant, wait for a person, or are refused, as Decionis decides, with chained evidence. Homebrew, Linux, Docker, Helm.

decionis
โญ 661 TypeScript ๐Ÿ‘ค decionis Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-08-13
21
secureagentics/Adrian

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

secureagentics
โญ 597 Python ๐Ÿ‘ค secureagentics Organization ๐Ÿ• Updated 2026-10-21 ๐Ÿ“… Created 2026-05-11
22
PrismorSec/prismor

Self-hosted runtime control plane for AI agents. Observe, approve with HITL, or block rogue tool calls before they executeโ€”preventing secret leaks, prompt injection, supply-chain attacks, and moreโ€”from a local dashboard. Agent-agnostic (Claude, Codex, LangChain, etc.).

PrismorSec
โญ 585 Python ๐Ÿ‘ค PrismorSec Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-20
23
graygnatconsole/mcp-audit-tool

๐Ÿ›ก๏ธ Security audit CLI for Model Context Protocol (MCP) servers โ€” scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.

graygnatconsole
โญ 543 Python ๐Ÿ‘ค graygnatconsole User ๐Ÿ• Updated 2026-10-24 ๐Ÿ“… Created 2026-09-26
24
emiliaprotocol/emilia-protocol

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.

emiliaprotocol
โญ 525 TypeScript ๐Ÿ‘ค emiliaprotocol Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2026-03-13
25
Justin0504/Aegis

Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.

Justin0504
โญ 524 TypeScript ๐Ÿ‘ค Justin0504 User ๐Ÿ• Updated 2026-10-31 ๐Ÿ“… Created 2026-03-04

Frequently Asked Questions

1

What is the most popular #agent-security repository on GitHub?

The top ranked open source #agent-security project on GitHub is NVIDIA/SkillSpector with 27,129 stars. 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.

2

Which programming languages are most used in #agent-security repositories?

Among the top ranked #agent-security projects on GitHub, the most common programming languages are Python, Rust, Go, TypeScript.

3

How is the #agent-security repository ranking calculated?

We track 25 active open source repositories tagged with #agent-security (500+ stars), totaling 76,391 stars with an average of 3,055 stars per repository. Rankings update daily from the GitHub API.