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 · 1,284個專案清除篩選
Generate least-privilege Claude Code permission rules for MCP tools from their live annotations: readOnlyHint tools go to allow, everything else to ask, one mcp__server__tool rule each, never a glob.
翻譯準備中
CI gate for Claude Code skills and plugins: scans a skills or plugin repository for instruction-override text, exfiltration patterns, dangerous hook commands, unpinned MCP servers and secret-shaped st
翻譯準備中
Pensar is a continuous adversarial testing platform: offensive AI agents attack your live systems, prove real exploits, and re-attack every fix until it holds.
翻譯準備中
Claude Code permission rule simulator: load the merged allow, ask and deny settings, show which rule decides any tool call, and find the bypasses: commands that slip past a Bash pattern, paths that es
翻譯準備中
Run Claude Code, Codex or pi in a secure Linux VM on your Mac. Your API keys never enter the sandbox, every connection follows your policy, and it pauses in 1 ms and wakes in 0.3 s.
翻譯準備中
AgentGuard is an open-source runtime firewall for AI agents. Wire-level enforcement at the protocol boundary — an MCP gateway and an LLM API proxy — with policy-as-code in YAML, human-in-the-loop appr
翻譯準備中
Proxed.AI is the simplest way to protect AI API keys in iOS apps. Lock down your API credentials, verify device authenticity with Apple's DeviceCheck, and structure AI outputs—all without a backend. O
翻譯準備中
CaMeL-style control/data-flow separation that reduces injection-to-effect risk under stated assumptions. Topology, not a safety certificate.
翻譯準備中
A security incident-response console: detections become diagnoses, diagnoses are challenged by evidence, and every response is scored and tiered before anyone acts.
翻譯準備中
Every AI employee. One workplace. Connect the bots you already run, set what they may do, and approve anything risky.
翻譯準備中
Cartographier les liens entre sociétés, dirigeants, adresses, événements juridiques et sanctions — avec niveau de preuve (confirmé, déclaré, inféré, simulé).
翻譯準備中
Open-source security tooling built by VardrSec: API authorization testing, attack surface mapping, and local scan automation.
翻譯準備中
Explore an extensive range of use cases supported by Fingerprint, and learn how to successfully implement it for your business with practical guidance and a comprehensive demo.
翻譯準備中
Every LLM interaction. Logged. Immutable. Attributed. Human-directed AI assistance with deterministic governance for chat and MCP tool calls. What Is LLM Provost? LLM Provost is a complete enterprise
翻譯準備中
Authentication, validation, fraud detection, payments intelligence, and global data, delivered through one unified API.
翻譯準備中
Pocket ID 是一個易於使用、自行託管的 OpenID Connect Certified™ 與 OAuth 2.0 提供者。使用者可使用通行金鑰而非密碼登入您的應用程式。
AI 翻譯
JumpServer 是广受欢迎的开源堡垒机与运维安全审计平台，支持主机、数据库、Kubernetes、RemoteApp 等资产统一纳管，覆盖 4A、PAM、数据库审计与合规场景。
翻譯準備中
Free, open-source, local-first scanner and integrity monitor for OpenClaw skills. npx ironheights scan ./skill
翻譯準備中
Blur unregistered faces in your live stream with InnoLive's real-time AI de-identification. Keep registered participants visible and try face privacy protection in your browser.
翻譯準備中
Disposable email that actually disappears. Spam-proof, encrypted, real-time. Like a burner phone, but for your inbox.
翻譯準備中
Free PDF redaction that really deletes text. Remove names, numbers and hidden metadata from PDFs without uploading them. No account, no watermark.
翻譯準備中
Native iOS proxy client (meow-rs) for iOS 18+. Clash-style YAML subscriptions, rule-based routing, DNS over HTTPS, QR-code profile sharing, and a SwiftUI material design in light and dark. Available o
翻譯準備中
開源、隱私優先，並為擴展而打造。Hanko 是你整合 passkeys、2FA、SSO 等的最快方式，且讓你完全掌控自己的資料。可隨時在自託管與 Hanko Cloud 之間切換。
AI 翻譯
Five AI agent tool calls, each followed through a real OPA policy compiled to WebAssembly and running in your browser: allowed, held for approval, or blocked.
翻譯準備中
用於 Keycloak 的 Kubernetes 運算子。以程式碼管理 realms、用戶端、使用者、角色與身分提供者。具備 GitOps 支援、自動密鑰同步與漂移偵測，並適用於 Keycloak 20-26+。
AI 翻譯
Open-source Rust kernel for AI agents: kernel-enforced permissions, hybrid post-quantum capability tokens, provable actions.
翻譯準備中
Forward or paste a suspicious email. A team of AI agents dissects it and returns an evidence-cited verdict: SCAM, SUSPICIOUS, or LIKELY SAFE.
翻譯準備中
Open source desktop app and Chromium extension for capturing, organizing, and verifying web evidence in OSINT investigations. Local-first, with SHA-256 hashes, a signed manifest, and RFC 3161 timestam
翻譯準備中
Free scanner for vibe-coded JS, TypeScript and Python apps: leaked keys, broken API routes, swallowed errors, vulnerable packages, PII leaks. Ranked fixes.
翻譯準備中
Generate audit-ready PDF and Word documentation for Microsoft Intune policies, settings, assignments, and security baselines with a free read-only tool.
翻譯準備中
Reads your existing coding-agent logs and turns them into clear answers about exposure, activity and cost. Local, read-only, no network.
翻譯準備中
OpenAI、Anthropic 等的合规閘道。企業自託管，將敏感資料保留在您的網路中，與系統提示文字分離。簽署收據。
AI 翻譯
Herramientas para gestionar la adecuación a la Ley 21.719 de protección de datos
翻譯準備中
AI 摘要 · 網站與 README
Queryable encryption for Postgres. Searchable field-level encryption with identity-bound keys, on the database you already use. The infrastructure for privacy-first applications.
翻譯準備中
msb-manager runs coding agents in per-project microVMs with deny-by-default egress and credentials that never enter the VM.
翻譯準備中
Security-first proxy for Large Language Models with multi-provider support, ring-based plugin pipeline, and real-time SOC dashboard.
翻譯準備中
Check a Supabase app's Row Level Security in about a minute. Real attacks on a private copy in your browser, with a fix file when one can be made. Free, no signup.
翻譯準備中
Locke is the Sonomos Early Access desktop app for x64 Windows and Linux. It screens AI websites through the Locke Extension and command-line, script and SDK traffic through a local proxy. macOS is com
翻譯準備中
A free, open-source VPN client for your subscription. Works with VLESS + Reality, VMess, Trojan, Shadowsocks, Hysteria2, TUIC and WireGuard, and with Remnawave, Marzban and 3x-ui subscriptions. For Wi
翻譯準備中
Let Claude Code, Cursor and Codex use your credentials without seeing them. Touch ID per credential, proxy calls, audit log. Open source, local, macOS.
翻譯準備中
A safety floor your AI agents can't get under: one policy for every agent, judged by what each call will run, backstopped by the kernel, with a signed record.
翻譯準備中
TRACE (Toolkit for Retrieval and Analysis of Cyber Evidence) is free, open-source digital forensics software. Open E01, AFF4 and raw disk images read-only, triage what stands out, recover deleted file
翻譯準備中
Compare data privacy, retention, and model training policies across major LLM providers, inference APIs, and AI coding tools.
翻譯準備中
Lets a person or organization govern their own AI agent through scoped, signed delegation
翻譯準備中
AI 摘要 · 審核時修訂
An open standard for AI agent identity — signed declarations and attestations that verify offline.
翻譯準備中
One folder Claude Code, Cursor and Codex all read over MCP. An agent reads only what its person can, every write is a version, and folders share outward.
翻譯準備中
Verify and issue EU Digital Identity Wallet credentials with one API call. Open source, runs on your servers, personal data stays with you.
翻譯準備中
Free scam shield for Indian elders and families. Paste a message and get a plain verdict: Safe, Be Careful, or Danger. English, Hindi, Hinglish. Runs on your device.
翻譯準備中
Baret simulates every Monad transaction before you or your AI agent signs it, checks it against your rules, and explains the verdict in plain words.
翻譯準備中
Explore SPDX 3 SBOMs as an interactive graph. Packages, source files, builds, tools, licenses... and every link between them.
翻譯準備中
Deterministic rules that enforce what your agents can do in real time, per user and per tool call, with live and after-the-fact analysis. Open source by Hexamind.
翻譯準備中
Ten open-source tools to scan, prevent, attack, investigate, gate and contain prompt-injection, MCP supply-chain and agent-to-agent attacks against AI agents.
翻譯準備中
Signed, tamper-evident records of what your AI agent decided and what it relied on. Anchored on Solana, checked by anyone in their own browser.
翻譯準備中
Secrets management for the agentic era. No more secrets in .env files. Self-hosted, no limits, free forever.
翻譯準備中
Keyorra is a free password manager for your Mac: an encrypted vault that never leaves it, and a browser extension that fills logins, cards and one-time codes.
翻譯準備中
Vulnerability-Lookup facilitates quick correlation of vulnerabilities from various sources, independent of vulnerability IDs, and streamlines the management of Coordinated Vulnerability Disclosure (CV
翻譯準備中
ScanX checks every QR code and barcode for scams before you open it, makes QR codes and gives you a Digital ID card you can share in one tap. Privacy-first: scanning works without an account.
翻譯準備中
Stenwatch is a free, open-source tool that narrows every public software flaw to the few that matter to your organisation, with a plain reason for each one.
翻譯準備中
Free Mac app that shows what your AI coding tools installed, checks their settings for problems, and tells you what's safe to clean up. It only looks.
翻譯準備中
Code checks 500 certificates exactly, Jev reads the ticket and judges only the few that matter, and a fixed policy decides. Every input, output and cent is shown.
翻譯準備中
Mailprogramm, Mailserver, SSH-Client, Remotedesktop, Passwortmanager mit eigenem Server, Editor und Bildschirmspiegeln: Open Source, ohne Telemetrie, mit Nyu der Katze. Ein Hobbyprojekt von Streamer M
翻譯準備中
BlindHop mixnet privacy layer for Substrate light clients. Toggle between direct, fast, and full metadata privacy modes. No setup required — runs in your browser.
翻譯準備中
SSO, MFA, passkeys, RBAC, and session management — built for developers, trusted by enterprises.
翻譯準備中
Subdomain enumeration you can trust. subenum classifies every DNS lookup, grades the run complete, degraded or unreliable, and ships as a single static Go binary.
翻譯準備中
One control room over open agent governance, running on your own infrastructure: per-action passkey kill switch, WireGuard remote, post-quantum signatures, and a local-first AI copilot. Apache-2.0, se
翻譯準備中
AI governance software covering 30+ frameworks: EU AI Act, ISO 42001, NIST AI RMF, GDPR. Inventory, risk, policy, evidence, LLM evaluation.
翻譯準備中
Find what your app accidentally exposed. Free, read-only scan of your live site. No signup.
翻譯準備中
Docudis finds names, emails, phone numbers, IBANs and addresses in your documents and replaces them with labels, on your phone, before you send them to an AI.
翻譯準備中
MITM proxy for reverse engineering — LLM-ready output, multi-language codegen, sign algorithm inference, request replay, plugin system, native desktop GUI (Wails + Svelte)
翻譯準備中
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
Built for safety-critical systems, our Trust Lifecycle Management platform delivers unified cybersecurity for IoT and embedded systems in one framework.
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
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