安全專案
正在載入…
安全專案
在程式碼倉庫中發現AI程式設計工具痕跡的公開專案，依最近收錄排序。
安全 · 1,316個專案清除篩選
Unofficial MCP server for the Sophos Fusion and Sophos Central APIs. Not a Sophos product and not supported by Sophos. 310 tools across 22 API namespaces, as a Claude Desktop extension or via npx.
翻譯準備中
Rapid7 Bulk Export MCP - AI-powered analysis for Rapid7 Command Platform data using MCP (Model Context Protocol) & AgentSkills.
翻譯準備中
Large Language Model (LLM) information redactor that prevents private information from being sent to LLMs from agentic tools by substituting placeholders for private information on outgoing requests a
翻譯準備中
Sequent is the world’s first online voting platform to ensure the highest level of confidence in elections for voters, election managers, and auditors
翻譯準備中
Vanity address mint for EVM and TRON. You make half the key on your own computer, we mint the other half on GPUs, and only you can put the full private key together.
翻譯準備中
One sealed envelope per person: a letter and the passwords they need, encrypted on your phone, opened only after months of silence. Open source, not audited.
翻譯準備中
AI IDE security hook: blocks directories, scans secrets, and protects AI interactions
翻譯準備中
Open-source crates for the Enclavia enclave runtime: in-enclave services, shared protocol types, client SDK, CLI. Dual-licensed Apache-2.0/MIT.
翻譯準備中
Klickbarer Prototyp: Pendelströme Konstanz–Kreuzlingen gemeinsam berechnen, ohne Rohdaten herzugeben (MPC, PSI, Differential Privacy) – mit Testdaten.
翻譯準備中
You can't govern what you can't see. Role mining and analytics that make sense of your authorization data — open source, self-hosted, your identity data never leaves your environment.
翻譯準備中
Verify two deployed randomness beacons from their real outputs: NIST Beacon 2.0 pulses (SHA-512 hash chain, skiplist, precommitment, RSA signature) and drand League of Entropy rounds (threshold BLS si
翻譯準備中
Security checks agents can call: MCP manifest preflight, source-pattern scanning and injection screening, with signed redacted receipts.
翻譯準備中
Browse, search, and explore all Microsoft Intune Settings Catalog definitions — fast, and without needing Intune access.
翻譯準備中
Establish trust on every request. Welcome real users and AI agents, stop abusive bots — GDPR-compliant, risk-based verification that minimises friction.
翻譯準備中
13 specialized AI agents, 30+ MCP integrations, 7,200+ detection rules. Apache 2.0. Local-first.
翻譯準備中
Live demo of the Risk, Fraud & Regulatory Intelligence Copilot. Runs in your browser with fake sample data; no Snowflake, no AI call.
翻譯準備中
Локальный AI-ассистент для аудита безопасности кода на Python, JavaScript/TypeScript и Go: находит уязвимости, классифицирует по CWE и OWASP Top 10 и предлагает проверенные исправления.
翻譯準備中
shard-core combines ChaCha20-Poly1305 with Shamir key sharing, resilient recovery, explicit secret output, Fordefi phrase workflows, and a verified offline build path.
翻譯準備中
From generation to distribution. Generate, manage, and share SBOMs and compliance documents. Integrate with GitHub, GitLab, and more. CRA & NTIA compliant.
翻譯準備中
Sealed evidence, reconstructed attack chains and the exact log line behind every finding, for Claude Code, Codex, Cursor, Gemini, Copilot and more. Open source.
翻譯準備中
v7.0: 4 lenses × 4 mindsets + consensus scoring. 90% precision, free. Plus interactive security assessment (39 verticals, 845 checks).
翻譯準備中
为 iPhone 而设计的私密卡片收藏空间。整理银行卡与全球账户，本机加密保存，随时欣赏你的收藏。QuanCard 全卡卡，现已开放 TestFlight 公开测试。
翻譯準備中
Network threat hunting for Zeek and Suricata logs. Explainable per-host risk scores with evidence chains and MITRE ATT&CK mapping. Reads your logs, never touches your network.
翻譯準備中
Sessions to the machines you already run, without an agent on them. Recorded, approved, audited.
翻譯準備中
Open-source ใช้ฟรี ทำงานบนเครื่องผู้เล่นเอง แสดงร่องรอยเป็นหลักฐาน ไม่ตัดสินแทนคน
翻譯準備中
Flash an ESP32-C5 board from the browser with the firmware that makes it a Kismet capture source for Wi-Fi, Zigbee/Thread and Bluetooth LE advertising.
翻譯準備中
A Wazuh alert fires at 3am and your IR playbook is a Markdown doc nobody executes, so steps get skipped and the ticket is a guess. Hotwash makes the same p
翻譯準備中
Memory, coordination, verification, and governance across a whole portfolio. We run our own company on it, and we publish the receipts.
翻譯準備中
PG1 Threat Intelligence: threat-intelligence tools for AI agents over MCP, A2A and REST, with free wallet, domain and hostname checks and a STIX 2.1 indicator feed paid per call with x402 on Base.
翻譯準備中
ReARM is a release governance platform: see what's in every release, whether it's cleared to ship functionally and security-wise, and the evidence proving both.
翻譯準備中
Security monitoring middleware for IChatClient — prompt injection, hallucination, and operational anomaly detection with an embedded dashboard.
翻譯準備中
Deterministic, graph-native threat modeling. Model your real stack, map exposures to MITRE ATT&CK, and produce citable evidence for DORA and NIS2.
翻譯準備中
Sanitised public demo of a read-only Microsoft 365 security operations console (FastAPI + Graph, 21 collectors). All data is synthetic and machine-verified.
翻譯準備中
Map Gen AI and Agentic security risks to industry frameworks. Score coverage across EU AI Act, FedRAMP, DORA, NIST, ISO, and 20 more. Submit any standard for automated mapping. Free, open-source, from
翻譯準備中
La compartimentation de Qubes, pour tout le monde. Des Espaces isolés, une couleur par Espace, aucune expertise requise.
翻譯準備中
Explainers on DNS-01 validation, wildcard certificates, CNAME delegation, deploy hooks and automated renewal, plus a documentation assistant that runs a local LLM over CertMate's docs. No credentials,
翻譯準備中
Scan Claude Code, Codex, Cursor and Gemini CLI logs for leaked API keys. Scrub them. Block the next one.
翻譯準備中
Check if a photo or video is real by verifying its camera signature and integrity directly in your browser without uploading files
翻譯準備中
AI 摘要 · 網站與 README
Paste your Wazuh custom rules and decoders and see, in your browser, what wazuh-analysisd 4.14.7 will warn about at load: rules ignored because a parent is missing or loads later, duplicate IDs, stati
翻譯準備中
Deterministic allow, deny or hold for every agent action over POST /v1/decide. Holds resolve through signed, cost-bound approval tokens; no LLM in the decision path. Validated live: 176 decisions, a 3
翻譯準備中
Three free checks: a suspicious message or prompt (read in your browser, never sent), a crypto token or wallet address across EVM, Solana, Sui and TRON, and an npm package before you install it. No ac
翻譯準備中
Démonstration de détection de fraude en assurance IARD, sur données fictives : règles de scoring, analyse réseau, lecture de rapport de police et dossier de recours. Refonte en cours.
翻譯準備中
A privacy-preserving JSON-RPC proxy for Ethereum nodes with ZK-proof authentication and hierarchical RBAC.
翻譯準備中
Privaro keeps your private photos and videos encrypted on your iPhone, behind Face ID and a passcode of its own. No account, nothing uploaded.
翻譯準備中
Healthcare-ops AI assistant where the harness, not the model, controls access, tools and actions. Role-scoped RAG, confirm-before-execute, audit traces, red-team and model-cost labs. Live demo.
翻譯準備中
Static-first, explainable PE triage with auto-synthesized YARA rules (never executes samples)
翻譯準備中
Universal catalog of offline-first defensive cybersecurity plugins, 18 specialist AI agent profiles, and deterministic verification tools for GitHub Copilot, Claude Code, and Codex.
翻譯準備中
AI-native correlation engine for enterprise SOC teams. Global feed coverage, MITRE ATT&CK mapping, STIX 2.1 export, API-first integration.
翻譯準備中
Open mini-CNAPP: code-to-runtime lifecycle graph, Zero-Trust policy (Python + Rego), trace-to-commit
翻譯準備中
Vérifiez les avis de concours, faux virements Mobile Money et faux visas avant d'envoyer votre argent.
翻譯準備中
當客戶的安全審查阻礙交易進度時，AI 安全工程師能找出攻擊者實際可觸及的範圍並撰寫修復程式；AI 滲透測試員則透過入侵來驗證結果。您只需核准每一項
AI 翻譯
Automatic protection against ransomware, human error and hardware failure. Your bucket, your keys. US$5 per server per month.
翻譯準備中
Prismo is a simple, open-source NFC/RFID access control system for hackerspaces and makerspaces. Control doors and machines with easy-to-build hardware and free software.
翻譯準備中
Read-only attack-path reasoning and remediation prioritisation over scanner, identity and exploit-intel data
翻譯準備中
A local-first security gateway for Claude Code and OpenAI-compatible coding agents. One Rust binary on 127.0.0.1: private keys and seed phrases redacted outbound, dangerous tool calls blocked inbound.
翻譯準備中
Guardbee scans your websites with AI, reports risk in business language, and BeeAI delivers on-the-spot fixes. 14-day free trial. Plans from $30/month.
翻譯準備中
OWASP Coraza 是開源、企業級、高效能的網頁應用防火牆，專為 APIs 與網頁應用設計，涵蓋從舊式到現代的應用。
AI 翻譯
x402 風險檢查供應商：簽署預付款裁決 — 包含 OFAC、網路釣魚資訊流、交易模擬、drainer-kit 程式碼，以及我們自有的 EIP-7702 套件監控（針對毒化者與掃蕩者）。使用預付點數進行檢查，每次費用為 $0.001。
AI 翻譯
The menu-bar radar for runaway, leaking and forgotten processes on your Mac. Free, open source, offline.
翻譯準備中
Your own model checks a draft report against the code it cites and returns one verdict: submit, rewrite then submit, prove first, hold as a duplicate, or drop.
翻譯準備中
A local-first workbench for OpenAI Codex Security: run, inspect, compare and govern AI-assisted security scans without losing the evidence, cost and
翻譯準備中
Download the DuckDuckGo browser to search and browse more privately. Available for Windows, Mac, iOS, and Android.
翻譯準備中
MSP Atlas: self-hosted IT documentation and an encrypted password vault for managed service providers, with per-client access and a read-only client portal.
翻譯準備中
AtlaSent protects consequential actions by people, software and AI: an enforceable decision before the action runs, and proof of what was decided and what happened after.
翻譯準備中
使用 pac4j 保障 Java 應用程式的安全：在 Spring Boot 與其他框架中提供 OpenID Connect、SAML、CAS、OAuth 與 JWT 的驗證與授權
AI 翻譯
KiberOgoh UZ — mahalla darajasidagi milliy kiber qalqon platformasi. Fuqarolarni onlayn firibgarlik va kiber tahdidlardan himoya qiladi.
翻譯準備中
Xencodes 是一個虛擬 SMS 驗證平台。搜尋您需要的服務，選擇國家，即可取得在數秒內接收簡訊驗證碼的虛擬號碼。以 NGN 按使用付費，
AI 翻譯
Hawkeye Sterling — 針對貴金屬與寶石交易商的 AML/CFT 實體風險評估：包含 0–30 分的結構化風險評分、CDD/SDD/EDD 判定、裝置端登記與雜湊鏈式稽核日誌。所有數據
AI 翻譯
Document-based age verification for online platforms with white-label flows, privacy-first by design, fair billing, and seamless integration via API or packages.
翻譯準備中
Agente de seguridad digital por WhatsApp. Links, CBU/CVU, teléfonos, correos y archivos analizados en minutos.
翻譯準備中
Check emails and URLs instantly. Detect phishing, fake addresses, and malware domains — free, no signup.
翻譯準備中
Encryption hides what a message says. SentinelSpread also hides that it was sent: AES-256-GCM, a real GNU Radio spread-spectrum link, and steganography in ordinary images and audio. 20 working tools.
翻譯準備中
Paste AI-generated text, see the invisible characters hidden in it, and copy a clean version. Runs entirely in your browser.
翻譯準備中
在呼叫之前檢查 AI 代理端點：只讀取、無 API 金鑰的信任檢查，根據觀測的可靠性證據返回機器可讀的 trustDecision。
AI 翻譯
免费检测你的网络出口：注册 Muse 前先看会不会进等候名单；Muse、Claude、ChatGPT、Gemini 各自看到的 IP 在哪、能不能用；住宅还是机房、DNS / WebRTC 有没有泄露、Claude Code 终端走哪个出口。每条问题都写明怎么改，无需登录。
翻譯準備中
Open-source agentic DFIR. Agents divide the case on a shared board, write their own tools, and leave a hash-chained record you can put in front of a court. Free under the AGPL.
翻譯準備中
OSS SIEM + XDR Powered by Threat intelligence and real time correlation. Built for 24x7 Security Operations with Automated Threat Detection and Response
翻譯準備中
Every MCP tool call journaled with secrets redacted, risky ones held until you approve. Self-hosted, Apache-2.0.
翻譯準備中
您的拉取請求已通過審查，但發佈的壓縮檔卻未經審查。Drydock 可比對精確的 npm、PyPI 或 VS Code 成品，並將供應鏈檢測結果標註在變更的程式碼行。
AI 翻譯
Verify Execution Receipts from Axeum Technologies using a receipt ID or public key
翻譯準備中
AI 摘要 · 網站與 README
tweetfeed.live MCP server (CF Worker) - 14 IOC threat-intel tools, 7 resources, 3 prompts, no auth, CC0 data. Endpoint: https://mcp.tweetfeed.live
翻譯準備中
Live IOC feeds for Threat Intelligence - URLs, domains, IPs, hashes. Real-time Twitter feeds, updated every 15 min.
翻譯準備中
Runs any program inside namespaces with no network interfaces, no routes, no DNS, plus capability dropping and a seccomp filter blocking network syscalls. Two Go modules, no runtime services.
翻譯準備中
Deterministic crypto inventory for Python wheels, with FIPS compatibility as one lens over it. It gathers evidence; it does not decide FIPS compliance.
翻譯準備中
Runs several independent, narrowly focused passes over every source file instead of one general “find bugs” prompt, then merges the results. Every file gets a recorded status and every failed pass is
翻譯準備中
ArgusAI is an AI-powered event detection system for home security. Analyze video feeds from UniFi Protect, RTSP, and USB cameras with multi-provider AI.
翻譯準備中
Vault is an open-source iPhone and iPad app for the secrets you can't afford to lose: 2FA codes, private notes and crypto recovery phrases. Fully offline, with encrypted backups and protection for whe
翻譯準備中
One read-only query in your Supabase SQL editor. Every open policy, table and function, quoted from your database, with the fix and the undo. Free.
翻譯準備中
Prismor intercepts every tool call your AI agents make, enforces security policies, and logs a full audit trail. Works with all enterprise AI agents.
翻譯準備中
SIQ Agent Security：面向 Agent Skills 的可信执行安全运行时。Skill 引导接入、本地 Go 程序裁决、宿主钩子执行保护，以 Ed25519 与 SHA-256 绑定授权、参数与回执；0.4.0 签名正式版已发布。
翻譯準備中
See who your AI talks to and decide who it does not. All on your computer: no account, no server, open source. Windows, Linux and macOS.
翻譯準備中
La preuve qualifiée eIDAS, ouverte, automatisable et protégée par des statuts intangibles. Un pilote tourne déjà. Livre blanc en consultation, appel à partenaires.
翻譯準備中
한국어 개인정보 비식별화 오픈소스 엔진 — 규칙+로컬 LLM 하이브리드 PII 탐지·마스킹 라이브러리, CLI, MCP 서버 (2026 오픈소스 개발자대회, 팀 마스킹테이프)
翻譯準備中
Check whether your email has been exposed in a data breach and get an AI-powered risk score with clear steps to reduce your exposure.
翻譯準備中
Signed receipts for vibe-coded data pipelines. Proves nobody changed your data, and shows the exact link if they did.
翻譯準備中
Vero 是開源零知識合規，用於 AI 代理付款。代理證明資格而非身分。MIT 授權。符合 FATF R.15/R.16。建構於 Open Wallet Standard。於 GitHub 分支。
AI 翻譯
開源隱私與批准閘道，供 AI 助手使用 (MCP)：人工批准、本地 PII 檢查與審計，支援 Gmail、Drive、Slack、Salesforce、Jira 等。
AI 翻譯
CyberArena is a live benchmark where two AI agents fight an attack-and-defense CTF: each one exploits the other's vulnerable service while patching its own, round after round. Watch live matches, repl
翻譯準備中
Records agent tool sequences on the laptop, attests coverage, forwards to your SIEM. Apache-2.0.
翻譯準備中
CRANE — self-hosted compliance management for the EU Cyber Resilience Act. SBOM analysis, vulnerability tracking, release gates and audit trails in one auditable platform.
翻譯準備中
Browse live police cameras on a map, filter by department, and build a video wall
翻譯準備中
AI 摘要 · 網站與 README
Write a team's threat model as text files in git, compiled and checked automatically
翻譯準備中
AI 摘要 · 審核時修訂
AI cloud video management for the cameras you already own: live streaming, 23 detections and scheduled virtual patrol rounds with a compliance record.
翻譯準備中
Task-scoped warrants that narrow as agents delegate. Every hop signed, every chain verifiable offline.
翻譯準備中
Streamline incident management with a comprehensive frontend that offers intuitive dashboards, investigation workflows, and real-time notifications for efficient response.
翻譯準備中
做出來了，現在該展示了。
在專案資料夾中執行一條命令即可。只要由AI輔助製作，就不必具備AI功能。
/nomorevibe查看收錄流程