Meta tags:
description=GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.;

Headings (most frequently used words):

agent, ai, this, threat, repositories, saved, searches, navigation, to, your, topic, footer, rehydra, lab, panguard, makerchecker, lelu, mythos, search, code, users, issues, pull, requests, provide, feedback, llm, security, menu, use, filter, results, more, quickly, here, are, 243, public, matching, improve, page, add, repo, keyvaluesoftwaresystems, opfor, adversa, secureclaw, rule, rules, jnmetacode, shellward, stackonehq, defender, gk0wk, clawguard, securelayer7, promptpurify, sdk, find, agentward, armorerlabs, armorer, gameworkerkim, cyber, intelligence, report, h4ckologic, bughunter, datacline, secure, mcp, gateway, opena2a, org, hackmyagent, akazah, prompt, anonymizer, null, square, behavior,

Text of the page (most frequently used words):
#security (78), llm (38), code (32), mcp (28), typescript (26), agent (23), updated (22), issues (22), 2026 (21), #prompt (21), agents (21), pull (21), requests (21), star (21), and (20), for (17), injection (17), open (14), source (13), openclaw (13), github (12), your (11), the (11), jul (11), owasp (10), threat (10), all (10), detection (8), guardrails (8), tool (7), pii (7), discussions (7), enterprise (7), you (6), topic (6), gateway (6), claude (6), audit (6), cybersecurity (6), view (6), this (5), privacy (5), with (5), topics (5), safety (5), secure (5), skills (5), control (5), rules (5), intelligence (5), search (5), that (4), community (4), more (4), use (4), red (4), lab (4), tools (4), data (4), before (4), scanner (4), may (4), agentic (4), platform (4), supply (4), chain (4), defense (4), stars (4), explore (4), support (4), can (3), manage (3), navigation (3), page (3), add (3), evaluation (3), engineering (3), anonymization (3), local (3), they (3), servers (3), access (3), cli (3), langchain (3), human (3), loop (3), policy (3), signed (3), sigma (3), find (3), runtime (3), calling (3), jun (3), plugin (3), secret (3), protection (3), most (3), repositories (3), another (3), tab (3), window (3), refresh (3), session (3), reload (3), sign (3), saved (3), documentation (3), feedback (3), grade (3), features (3), copilot (3), solutions (3), footer (2), learn (2), repo (2), developers (2), experiment (2), teaming (2), framework (2), across (2), behavior (2), first (2), extension (2), prompts (2), team (2), testing (2), scan (2), fix (2), governance (2), gdpr (2), every (2), server (2), devsecops (2), vulnerability (2), guards (2), mythos (2), authorization (2), engine (2), review (2), lelu (2), role (2), based (2), self (2), hosted (2), static (2), approvals (2), logs (2), makerchecker (2), users (2), skill (2), panguard (2), burp (2), suite (2), autonomous (2), bug (2), bounty (2), powered (2), track (2), type (2), web3 (2), cyber (2), zero (2), day (2), cti (2), korea (2), osint (2), archive (2), reports (2), agentward (2), model (2), rehydra (2), firewall (2), jailbreak (2), application (2), securelayer7 (2), actions (2), leaks (2), direct (2), shellward (2), 数据出境 (2), garak (2), top (2), secureclaw (2), adversary (2), emulation (2), recently (2), fewest (2), forks (2), sort (2), 243 (2), filter (2), language (2), sponsors (2), events (2), collections (2), trending (2), appearance (2), settings (2), cancel (2), see (2), available (2), searches (2), business (2), advanced (2), developer (2), resources (2), customer (2), services (2), devops (2), app (2), perform, action, time, not, share, personal, information, cookies, contact, docs, status, terms, inc, associate, repository, visit, landing, select, curate, description, image, links, easily, about, improve, load, tracking, prisma, react, controlled, studying, how, using, behave, vary, personas, conversation, histories, run, repeated, trials, models, measure, effect, call, null, square, transformers, chatgpt, pseudonymization, presidio, tauri, webgpu, openai, japanese, chrome, buddy, check, reach, device, reversible, catches, didn, mean, send, anonymizer, akazah, penetration, metasploit, attack, toolkit, hackmyagent, opena2a, org, infra, stable, groups, logging, infrastructure, minimal, efforts, datacline, dast, sast, appsec, rego, token, confidence, aware, gating, full, trail, trails, analysis, cryptography, enforce, rbac, segregation, duties, cryptographically, offline, verifiable, poisoning, yara, audits, install, monitors, shares, 開源安全平台, 安裝前審計, 即時監控, 社群共享威脅情報, anthropic, playwright, offensive, pentesting, hacking, hunting, state, machine, orchestration, credential, vault, hunt, target, com, let, bugs, bughunter, h4ckologic, independent, tlp, green, dprk, apt, threats, breach, multilingual, dennis, kim, report, gameworkerkim, nanoclaw, devtools, sandbox, docker, plane, running, sandboxes, credentials, health, armorer, armorerlabs, depth, built, hardened, prevent, accidental, leakage, hit, sdk, ctf, guardrail, applications, compact, outperforms, larger, regex, signatures, demo, anton, net, promptpurify, mar, scanning, loss, prevention, antivirus, approve, dangerous, block, keep, humans, 101, clawguard, gk0wk, indirect, via, function, detect, defend, against, attacks, 22mb, cpu, only, 10ms, latency, 108, defender, stackonehq, hermes, exfiltration, dlp, cursor, 应用合规网关, 一行命令体检, 项目的, 硬编码密钥, 个人信息暴露, 网安法, pipl, 等保2, ai标识, 并给出境内模型替代建议, 可作运行时防护拦截注入与数据外泄, 中文优先, 零依赖, 123, jnmetacode, standard, like, but, 425, shipped, microsoft, agt, cisco, misp, recall, nvidia, nist, oscal, path, 311, rule, apr, aligned, 348, adversa, browser, 563, opfor, keyvaluesoftwaresystems, least, options, java, jupyter, notebook, shell, rust, html, javascript, python, 202, 169, here, are, public, matching, message, dismiss, alert, switched, accounts, out, resetting, focus, create, qualifiers, our, query, name, results, quickly, submit, include, email, address, contacted, read, piece, take, input, very, seriously, provide, syntax, tips, clear, jump, pricing, premium, ons, program, accelerator, maintainer, programs, fund, partners, trust, center, forum, insights, ebooks, webinars, stories, software, development, industries, government, manufacturing, financial, healthcare, industry, cases, modernization, case, nonprofits, startups, small, medium, teams, enterprises, company, size, marketplace, changelog, blog, why, stop, start, build, vulnerabilities, changes, plan, work, instant, dev, environments, codespaces, automate, any, workflow, workflows, integrate, external, registry, new, from, issue, merge, write, better, creation, toggle, menu, skip, content,

Text of the page (random words):
llm security github topics github skip to content navigation menu toggle navigation sign in appearance settings platform ai code creation github copilot write better code with ai github copilot app direct agents from issue to merge mcp registry new integrate external tools developer workflows actions automate any workflow codespaces instant dev environments issues plan and track work code review manage code changes application security github advanced security find and fix vulnerabilities code security secure your code as you build secret protection stop leaks before they start explore why github documentation blog changelog marketplace view all features solutions by company size enterprises small and medium teams startups nonprofits by use case app modernization devsecops devops ci cd view all use cases by industry healthcare financial services manufacturing government view all industries view all solutions resources explore by topic ai software development devops security view all topics explore by type customer stories events webinars ebooks reports business insights github skills support services documentation customer support community forum trust center partners view all resources open source community github sponsors fund open source developers programs security lab maintainer community accelerator github stars archive program repositories topics trending collections enterprise enterprise solutions enterprise platform ai powered developer platform available add ons github advanced security enterprise grade security features copilot for business enterprise grade ai features premium support enterprise grade 24 7 support pricing search or jump to search code repositories users issues pull requests search clear search syntax tips provide feedback we read every piece of feedback and take your input very seriously include my email address so i can be contacted cancel submit feedback saved searches use saved searches to filter your results more quickly name query to see all available qualifiers see our documentation cancel create saved search sign in sign up appearance settings resetting focus you signed in with another tab or window reload to refresh your session you signed out in another tab or window reload to refresh your session you switched accounts on another tab or window reload to refresh your session dismiss alert message explore topics trending collections events github sponsors llm security star here are 243 public repositories matching this topic language typescript filter by language all 2 169 python 1 202 typescript 243 javascript 85 html 74 go 72 rust 62 shell 46 jupyter notebook 42 c 8 java 8 sort most stars sort options most stars fewest stars most forks fewest forks recently updated least recently updated keyvaluesoftwaresystems agent opfor star 563 code issues pull requests open source adversary emulation for ai agents and mcp servers cli typescript mcp jailbreak owasp browser extension red team ai agents security testing adversary emulation ai security prompt injection llm security owasp llm top 10 agentic ai mcp server ai red teaming updated jul 15 2026 typescript adversa ai secureclaw star 348 code issues pull requests secureclaw security plugin and skill for openclaw owasp aligned owasp ai agents ai security llm security owasp llm top 10 agentic ai openclaw openclaw skills openclaw security openclaw plugin updated apr 12 2026 typescript agent threat rule agent threat rules star 311 code issues pull requests discussions open detection standard like sigma but for ai agents 425 rules shipped in microsoft agt cisco ai defense misp owasp a s r h 97 1 recall on nvidia garak nist oscal path 1 owasp ai security threat detection sigma rules prompt injection llm security agent security mcp security garak owasp agentic agent threat rules updated jul 15 2026 typescript jnmetacode shellward star 123 code issues pull requests ai 应用合规网关 一行命令体检 ai 项目的 数据出境 硬编码密钥 个人信息暴露 网安法 pipl 等保2 0 数据出境 ai标识 并给出境内模型替代建议 可作运行时防护拦截注入与数据外泄 中文优先 零依赖 开源 security mcp cursor dlp ai safety data exfiltration ai security guardrails pii detection ai agent langchain prompt injection llm security agent security claude code mcp security ai firewall openclaw hermes agent shellward updated jun 23 2026 typescript stackonehq defender star 108 code issues pull requests open source prompt injection protection for agents calling tools via mcp cli or direct function calling detect and defend against prompt injection attacks 22mb cpu only 10ms latency ai security prompt injection llm security mcp security prompt injection defense prompt injection detection indirect prompt injection prompt injection protection updated jul 7 2026 typescript gk0wk clawguard star 101 code issues pull requests the antivirus for openclaw approve dangerous actions scan skills block secret leaks and keep humans in control for safety open source cybersecurity audit logs human in the loop policy engine data loss prevention ai security runtime security guardrails secret scanning supply chain security prompt injection llm security agent security openclaw updated mar 20 2026 typescript securelayer7 promptpurify star 76 code issues pull requests prompt injection guardrail for llm applications compact model that outperforms larger open source guards no regex no signatures demo anton securelayer7 net security application security ctf ai safety jailbreak detection ai security guardrails prompt engineering prompt injection llm security llm guardrails ai firewall prompt injection detection updated may 31 2026 typescript rehydra ai rehydra sdk star 76 code issues pull requests discussions prevent accidental pii leakage in llm prompts before they hit the model privacy gdpr pii ai security llm security updated jun 9 2026 typescript find lab agentward star 62 code issues pull requests agentward built for all hardened for openclaw defense in depth llm agent llm security agent security prompt injection defense openclaw openclaw security openclaw plugin updated jun 4 2026 typescript armorerlabs armorer star 58 code issues pull requests discussions local control plane for running ai agents with sandboxes approvals guardrails credentials and runtime health docker sandbox devtools self hosted cybersecurity ai agents ai security guardrails local first supply chain security llm security tool calling agent security agent runtime openclaw nanoclaw updated jul 14 2026 typescript gameworkerkim cyber threat intelligence report star 54 code issues pull requests independent osint cti archive tlp green supply chain zero day dprk apt ai llm threats web3 and korea breach policy reports multilingual kr en jp zh by dennis kim osint cybersecurity korea cti zero day threat intelligence cyber threat intelligence supply chain security llm security web3 security updated jul 13 2026 typescript h4ckologic bughunter ai star 52 code issues pull requests autonomous bug bounty hunting framework powered by claude code 20 ai agents state machine orchestration burp suite mcp credential vault llm security track type hunt target com and let ai find the bugs security hacking owasp cybersecurity bug bounty autonomous pentesting offensive security ai agents claude vulnerability scanner burp suite playwright anthropic llm security claude code updated may 19 2026 typescript panguard ai panguard ai star 52 code issues pull requests discussions open source security platform for ai agents audits skills before install monitors 24 7 shares threat intelligence across all users ai agent 開源安全平台 安裝前審計 skill 24 7 即時監控 社群共享威脅情報 open source typescript mcp cybersecurity yara threat intelligence ai security threat detection sigma rules ai agent prompt injection llm security tool poisoning updated jul 14 2026 typescript makerchecker makerchecker star 47 code issues pull requests open source security gateway static scanner for ai agents enforce role based access control rbac human in the loop approvals segregation of duties and cryptographically signed offline verifiable audit logs open source security cryptography mcp static analysis self hosted role based access control governance ai agents audit trails langchain llm security agentic ai updated jul 13 2026 typescript lelu ai lelu star 43 code issues pull requests discussions open source authorization engine for ai agents confidence aware gating human in the loop review policy as code full audit trail open source ai authorization token ai agents guardrails rego langchain llm security ai guardrails agent security updated jul 15 2026 typescript mythos agent mythos agent star 38 code issues pull requests discussions the ai security agent guards your code cli security typescript ai mcp scanner owasp cybersecurity vulnerability appsec devsecops sast dast ai agent llm security mcp server updated may 23 2026 typescript datacline secure mcp gateway star 34 code issues pull requests secure mcp infrastructure to audit and control every data access by ai agents with minimal efforts gdpr ai security audit logging secure ai ai governance llm security ai gateway ai security tool mcp servers mcp tools claude mcp mcp gateway claude skills secure mcp gateway mcp groups enterprise mcp gateway stable mcp mcp infra updated may 13 2026 typescript opena2a org hackmyagent star 32 code issues pull requests metasploit for ai agents scan attack and fix ai agents and mcp servers open source security toolkit tool mcp penetration testing security scanner red team ai agents ai security prompt injection llm security agent security mcp security updated jul 7 2026 typescript akazah prompt anonymizer star 27 code issues pull requests discussions a buddy check for your prompts before they reach an llm on device reversible anonymization that catches the pii you didn t mean to send chrome extension privacy japanese openai data privacy webgpu anonymization pii tauri presidio pii detection local first pseudonymization pii anonymization llm prompt engineering chatgpt llm security llm privacy transformers js updated jul 15 2026 typescript null square agent behavior lab star 26 code issues pull requests a controlled experiment lab for studying how tool using llm agents behave vary tools personas and conversation histories run repeated trials across models and measure the effect on safety and tool call behavior react typescript ai safety evaluation framework ai agents prisma red teaming tool use experiment tracking llm prompt engineering llm security llm evaluation agent evaluation updated jul 2 2026 typescript load more improve this page add a description image and links to the llm security topic page so that developers can more easily learn about it curate this topic add this topic to your repo to associate your repository with the llm security topic visit your repo s landing page and select manage topics learn more footer 2026 github inc footer navigation terms privacy security status community docs contact manage cookies do not share my personal information you can t perform that action at this time