llm-security repositories
Trending repositories tagged llm-security, ranked by trending score. Updated daily.
-
1
usestrix/strix
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
GitHub · Python · 76,747 stars · 8,739 forks · +370 stars in 24 hours · Trending score 5.02
-
2
Yeti-791/Awesome-Offensive-AI-Agentic-Landscape
This document curates open-source projects, academic papers, capability benchmarks, and commercial solutions (international & China) in AI penetration testing, LLM red teaming, autonomous offensive agents, and vulnerability discovery—aimed at helping researchers, security engineers, and enterprise decision-makers quickly form a holistic view.
GitHub · 487 stars · 62 forks · +385 stars in 24 hours · Trending score 4.80
-
3
qybaihe/bla
🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA).
GitHub · TypeScript · 6,260 stars · 778 forks · +154 stars in 24 hours · Trending score 4.42
-
4
NVIDIA/garak
the LLM vulnerability scanner
GitHub · Python · 10,091 stars · 1,491 forks · +185 stars in 24 hours · Trending score 4.03
-
5
ifixai-ai/iFixAi
Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.
GitHub · Python · 46,281 stars · 1,828 forks · +76 stars in 24 hours · Trending score 4.01
-
6
ZXEB/dsh-purge
dsh-purge v1.1.71 完整源码镜像(原仓库 YuJunZhiXue/dsh-purge 与 npm 包均已删除)。DeepSeek Harness 破甲 / 红队评测插件,支持官方 web 与桌面宿主。
GitHub · JavaScript · 554 stars · 547 forks · +58 stars in 24 hours · Trending score 3.76
-
7
ASCIT31/Dark-Moon
Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). Runs on a local LLM behind a Privacy Gateway. Integrates with GitHub, GitLab, Jenkins, VS Code, JetBrains, n8n, Grafana & Splunk.
GitHub · Python · 1,274 stars · 222 forks · +121 stars in 24 hours · Trending score 3.67
-
8
PrismorSec/prismor
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
GitHub · Python · 581 stars · 72 forks · +88 stars in 24 hours · Trending score 3.33
-
9
awarexone/Agentic-Bug-Hunter
AI-powered bug bounty hunting toolkit that works with or without subscription.
GitHub · Python · 6,011 stars · 1,102 forks · +33 stars in 24 hours · Trending score 3.27
-
10
CyberStrikeus/CyberStrike
Open-source AI-powered offensive security harness for automated penetration testing.
GitHub · TypeScript · 3,660 stars · 640 forks · +40 stars in 24 hours · Trending score 3.25
-
11
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.
GitHub · Python · 7,594 stars · 780 forks · +45 stars in 24 hours · Trending score 3.20
-
12
xqpsec/dsh-jailbreak
dsh jailbreak - DeepSeek Assistant 破甲插件(DSH 破甲 / 越狱 / 破甲提示词):请求边界注入,模型不再一开口就是「我不能」。20 类合并 ASR 45.0%、覆盖率 19/20、良性能力 Δ=0.0pt(24/24 判分);0 处宿主补丁、默认关闭、off 逐字透传、每次改写落 manifest 与 promptSha256 可审计。旧名 dsh-jalibreak
GitHub · JavaScript · 285 stars · 57 forks · +20 stars in 24 hours · Trending score 2.75
-
13
nolabs-ai/nono
agent runtime security - zero trust, zero setup, zero latency agent sandboxing
GitHub · Rust · 5,050 stars · 338 forks · +17 stars in 24 hours · Trending score 2.64
-
14
Cygnux-Labs/Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
GitHub · Python · 722 stars · 131 forks · +6 stars in 24 hours · Trending score 2.40
-
15
beelzebub-labs/beelzebub
A secure low code deception runtime framework, leveraging AI for System Virtualization.
GitHub · Go · 2,253 stars · 222 forks · +17 stars in 24 hours · Trending score 2.30
-
16
NVIDIA-NeMo/Guardrails
NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.
GitHub · Python · 7,534 stars · 905 forks · +11 stars in 24 hours · Trending score 2.28
-
17
lemonadesaltbagel/veil
Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.
GitHub · Python · 247 stars · 35 forks · +8 stars in 24 hours · Trending score 2.18
-
18
depalmar/ai-dfir-toolkit
A vendor-neutral collection of Sigma, YARA, and Suricata rules for detecting compromise of LLM applications, MCP servers, ML supply chains, AI infrastructure, AI-powered insider threats, and RAG/vector database attacks.
GitHub · Python · 179 stars · 27 forks · +19 stars in 24 hours · Trending score 2.05
-
19
Agent-Threat-Rule/agent-threat-rules
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
GitHub · TypeScript · 439 stars · 70 forks · +12 stars in 24 hours · Trending score 1.96
-
20
pktq/lasik
BLA blinds your agent. LASIK gives it its sight back. Static de-blinding CLI + MCP server that undoes BLA (Blind LLM Agents) hardening so coding agents and REA can read the real code again. Never executes the target.
GitHub · TypeScript · 142 stars · 14 forks · +5 stars in 24 hours · Trending score 1.82
-
21
1276486/ZERO-X-Bypass-Jailbreak
ZERO-X破甲 · AI 客户端破甲工具:Codex / Claude / Cursor / OpenCode / WorkBuddy / DeepSeek / 豆包 一键注入指令集。覆盖免杀 · EDR 绕过 · Shellcode · 加载器 · Webshell · 远控 · C2 · 反调试 · 反虚拟机 · 反沙箱 · 提权 · 内网渗透 · 横向移动 · 渗透测试 · 逆向工程 · 破解 · 卡密校验 · 样本分析 · 提示词注入 Prompt Injection · AI 越狱 AI Jailbreak · CVE · PoC · RCE · SSRF。Windows 桌面(Electron + React)
GitHub · PowerShell · 36 stars · 6 forks · +22 stars in 24 hours · Trending score 1.68
-
22
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.
GitHub · Go · 1,009 stars · 113 forks · +7 stars in 24 hours · Trending score 1.63
-
23
sunilgentyala/aegis-integrity
Free, local-first academic integrity checker and MCP server: citation hallucination detection, AI-text and plagiarism signals, venue guideline checks (IEEE, ACM, Elsevier). Documents never leave your machine.
GitHub · Python · 23 stars · 9 forks · +6 stars in 24 hours · Trending score 1.62
-
24
AGGIB/Stroq
Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky commands to the content that dictated them. Open source, no telemetry.
GitHub · TypeScript · 256 stars · 22 forks · +5 stars in 24 hours · Trending score 1.59