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 · 1,340個專案清除篩選
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
Diagnóstico e correção de vulnerabilidades em sistemas web para PMEs e fintechs. OWASP Top 10 · TLS · LGPD art. 46. Suíte de ferramentas open source.
翻譯準備中
Open-source credential broker that issues short-lived SSH, AWS, GitHub, and Kubernetes credentials after FIDO2 hardware verification.
翻譯準備中
SOVP 是確定性的 AI 基礎架構認證標準：包含 180 多個參數、三種狀態判定，並經由 Ed25519 簽署。美國專利申請中。
AI 翻譯
Esver OS turns repeated company workflows into verified executable skills. Visage keeps identity local. Mr. Haven keeps capital programmable.
翻譯準備中
Your .env files hold only references. The real values live in an encrypted vault on your machine. No account, no cloud, no telemetry.
翻譯準備中
Écosystème open source pour reprendre la main sur son droit, son identité, sa sécurité et son économie.
翻譯準備中
Approval gates and runtime authorization for AI coding agents. Decide what agents such as Claude Code, Codex and Cursor may do, what is denied, and what requires human approval — decided before integr
翻譯準備中
簡短、供應商中立的指南，說明硬體安全金鑰的實際功能——FIDO2 通行碼、TOTP、智慧卡（PIV）與 OpenPGP——如何設定以及在哪裡閱讀正式標準。
AI 翻譯
A self-hosted OpenID Connect provider with a bundled OpenLDAP directory and a web management UI. One login for your modern apps, one LDAP directory for the rest, no phone-home.
翻譯準備中
Secure how software is built in the age of AI agents. Govern what agents use, control what they do, and ensure trusted output - without slowing development.
翻譯準備中
A sanctions-screening audit: which way of comparing names, and where you set the bar, measured on your own alert history.
翻譯準備中
Slips 是一款免費軟體的行為 Python 入侵防禦系統 (IDS/IPS)，利用機器學習來偵測網路流量中的惡意行為。由 Stratosphere Laboratory, AIC, FEL, CVUT 開發。
AI 翻譯
Compartilhe a sessão já autenticada, cifrada com AES individual. Quem recebe entra em um clique. Você revoga quando quiser.
翻譯準備中
A fruit-fly escape reflex, compiled to 173 NAND gates and 6 latches, evaluated gate by gate in your browser inside a voxel world.
翻譯準備中
一個統一、單一指令即可完成的 SSO 管理員與 OIDC 反向代理技術棧，適用於家庭實驗室與小型企業。透過單一 setup.sh 即可將自託管身分提供者與反向代理整合在一起。
AI 翻譯
Free read-only Lite lists every custom Wazuh rule that never fired and the likely reason, including rules dropped at load (7617/7619).
翻譯準備中
A web management tool that supplements the Wazuh Dashboard: agents, groups, cluster nodes, rules and decoders, ready-made detection packs, API users and logs. Bilingual English / 繁體中文, AGPL-3.0.
翻譯準備中
您的基礎設施，隱於地圖之外。qURL Connector 可將您的應用程式與 APIs 從公開掃描中隱藏。只需一次 API 調用，即可為人員或 AI 代理建立私密訪問鏈接，並可自定義範圍、有效期與會話。
AI 翻譯
ThreatLens simulates realistic SOC investigations across identity, endpoint, email, and cloud — and grades your investigation against a hidden ground truth. Not a SIEM. A cyber range for analysts.
翻譯準備中
Evidence-first network configuration auditing: every authoritative finding cites the configuration line that proves it.
翻譯準備中
Check an OpenCloud instance for known vulnerabilities, missing hardening, weak security headers and available updates. Free to use, with no account required.
翻譯準備中
GameDay testing for MCP servers. Four named experiments over the JSON-RPC wire, in a sandbox, with scripted and local-model seats. Receipts, tapes and a dataset come out. The oracle is the wire, not t
翻譯準備中
Holdcall sits between your agent and its MCP tools. It decides every call on your machine, shows you the real arguments before anything dangerous runs, and keeps a record you can verify offline.
翻譯準備中
A small key that plugs into USB. Touch it to unlock, approve and authenticate — never a password.
翻譯準備中
Every connection across the organisation, wherever it runs, protected against tomorrow's decryption. Control stays in-house, always.
翻譯準備中
Get real SIM-based temporary phone numbers instantly. Receive SMS verification codes for 1,300+ services across 150+ countries. Pay only when a code arrives — automatic refund if it doesn't.
翻譯準備中
Manage your Keycloak from your AI assistant: clusters, realms, apps, SSO, custom domains, WAF, webhooks and SIEM. One command, browser sign-in, no API key.
翻譯準備中
Detection rules (Sigma-compatible core), real-time Endpoint Security, behavioural scoring, AI coding guardrails, and Agent Traces — W3C TRACEPARENT correlation between AI-agent activity and kernel eve
翻譯準備中
Agadar — scam-message detection for Sorani Kurdish and Iraqi Arabic, with the reasoning shown. Runs entirely in your browser. Python, scikit-learn, char n-grams.
翻譯準備中
An open standard letting a nonprofit publish, from its own domain, a machine-readable declaration of the giving destinations it authorizes. Consumed by AI agents through W3C WebMCP.
翻譯準備中
Działa na Twoim komputerze. 98,9% pełnych nazwisk, 23 rodzaje numerów, podmiany odwracalne.
翻譯準備中
Cognitive Deterministic Memory Security OS for Agentic AI that reaches backward through time to find the quiet change behind today's failure, not the lookalike. Intelligence is not a cloud subscriptio
翻譯準備中
SkillSpector 是 AI 代理技能的安全掃描器。偵測 Claude Code、Codex 與 MCP 技能中的漏洞、惡意模式、安全風險、提示注入、資料外洩與供應鏈風險。
AI 翻譯
OpenAI 的 Codex Security CLI 與 TypeScript SDK 用於偵測、驗證與修復安全漏洞。npm: https://www.npmjs.com/package/@openai/codex-security
AI 翻譯
An execution-authority gateway for AI agents and APIs. It intercepts consequential HTTP actions, asks Decionis whether they are authorized, and forwards exactly the authorized request once on a single
翻譯準備中
pinact 是一款用於編輯 GitHub Workflow 與 Composite action 檔案，並固定 Actions 與 Reusable Workflows 版本之 CLI。pinact 還可以更新它們的版本並驗證版本註解。
AI 翻譯
Single-file browser client for the Have I Been Pwned API. No API key, no backend. Passwords are hashed locally and only a 5-character SHA-1 prefix is ever sent.
翻譯準備中
Recover ZecWallet Lite seeds, zcashd wallet.dat files, and standalone Sapling or Sprout keys with a local-first desktop flow.
翻譯準備中
Free sanctions screening, PEP checks, and adverse media search tool. Plus a comprehensive AML Knowledge Hub covering MLR 2017, POCA 2002, and FCA compliance. Built for compliance professionals.
翻譯準備中
Something feels off? Check the vibe. A second opinion for messages, profiles, invitations and offers: warning signs of scams, grooming, coercion and exploitation, and where to get help.
翻譯準備中
106 curated security scans of open-source AI agents, MCP servers and LLM apps - 24 confirmed fixes, run local-first with Semgrep, Gitleaks, Trivy and pip-audit.
翻譯準備中
The Kubernetes-native policy enforcement plane for MCP. Deterministic admission and egress policy, attributable audit, and SIEM export — MIT, self-hosted, no SaaS.
翻譯準備中
Sandboxes isolados e descartáveis para agentes de IA: MCP, CLI, dashboard web e app nativo de macOS. Rede desligada por padrão, allowlist de domínios e trilha de auditoria. Go + SwiftUI.
翻譯準備中
Face ID-style unlock for Omarchy: the infrared camera recognises you at the lock screen, at sudo and in polkit, while your password stays the real key.
翻譯準備中
Open-source Aadhaar, PAN, GSTIN & UPI detection and reversible masking for AI prompts. Runs on your infrastructure. MIT.
翻譯準備中
The primary threat is accidental destruction — an agent that misreads a path and deletes the wrong folder — not a determined attacker. Network isolation is secondary and off by default; an AI CLI that
翻譯準備中
CI/lock collects trusted telemetry across every checkpoint between commit and production — CI/CD builds, security scans (SAST/DAST/SBOM), runtime + cluster integrity (Falco, Linkerd mTLS, kube-bench),
翻譯準備中
The local-first credential vault your AI agents can use — but never see. 66 testable security constraints. Rust.
翻譯準備中
AI Agent City is the operations layer for the agent economy: spending limits, monitoring, security, trust, and discovery for AI agents. Human-readable and machine-readable.
翻譯準備中
GDPR Chapter V Transfer Impact Assessment skill for Claude — EDPB six-step methodology, CNIL three-way Step 3, four essential guarantees, 12 country profiles, balanced Art. 49 analysis, RoPA interchan
翻譯準備中
GDPR Breach Response Sentinel Agent Skill (open standard) — ENISA severity assessment, EDPB case matching, Art. 33/34 notification support, audit-ready .docx generation
翻譯準備中
Read-only macOS notch + menu bar monitor for Claude Code and Codex. Open source, free, local-only. Risk-scores every tool call and tracks the footholds agents leave behind.
翻譯準備中
A policy-enforcing filesystem for AI agents. Point it at a real project directory and it serves a filtered mirror — same paths, same sizes — deciding per read which face of each file to show.
翻譯準備中
Low-latency bot detection for Apache 2.4 with proof-of-work challenges, shared-memory reputation, crawler policy, and built-in observability.
翻譯準備中
Short-lived SSH certificates from your identity provider, for ssh, sudo, and the console.
翻譯準備中
mcp-skills-vault installs MCP servers safely. mcp-trace shows what they're actually doing. Offline-first. No telemetry.
翻譯準備中
Belay is a local-first security layer at the tool-call boundary of AI coding agents. Deterministic, sub-100ms, fail-closed. Detect, block, and get notified — no LLM in the decision path.
翻譯準備中
Hub + agent + cihaz entegrasyonları: canlı paket ölçümü, süreç bazlı L7/DNS görünürlüğü, TimescaleDB + NATS ölçek altyapısı, RBAC/SSO, 5651 uyumlu imzalı loglar. Açık kaynak, MIT, kendi altyapınızda.
翻譯準備中
A deny-by-default contract layer for AI agent tool calls - strict argument validation, ghost-argument stripping and self-healing retries, in-process and Pydantic-only
翻譯準備中
Govern connected AI clients, models, and tools on your infrastructure. Centralize access policies and audit, then build custom capabilities on the SystemPrompt runtime.
翻譯準備中
Free, open-source CLI and MCP server that keeps API keys in your OS keychain and serves them to Cursor, Claude Code, and Kiro. No cloud, no account, no .env file.
翻譯準備中
AI security from risk map to reference architecture: the full CoSAI taxonomy, the MITRE mitigations that support its controls, and target-state architectures for every class of AI application.
翻譯準備中
A rubber band around Claude's claws. Blocks rm -rf and other destructive commands before they run, so bypassPermissions mode is actually safe.
翻譯準備中
Collective discovery for open cryptographic challenges. Contribute GPU time to a public elliptic-curve search, earn credit for verified work, share the prize when the answer is found.
翻譯準備中
Choose the assets. Run applicable upstream security checks. Read one report organized by asset and priority.
翻譯準備中
測試您的 vibe-coded 應用程式，獵捕幻覺套件、邏輯錯誤與秘密洩漏，並在數秒內修復。支援在 Cursor、Claude Code、GitHub Copilot 與 Windsurf 中運行。
AI 翻譯
Small Print is a nightly record of the tool descriptions, schemas and instructions that MCP servers, agent skills and plugins give your agent: every version hashed, every change diffed and graded by a
翻譯準備中
Sane WordPress defaults with actionable Site Health reporting for security, privacy, performance, and core updates — including same-line security patches.
翻譯準備中
The archive feature Graylog Open is missing — self-hosted, streaming, with independent compliance audit.
翻譯準備中
AI Ops for Bring Your Own Agent (BYOA) teams. Audit coworker harnesses with doorman dashboard, mine prompt history for capability needs, and block rogue tools at the gate.
翻譯準備中
Install Know Your Agent with npx in minutes. Offline demo, MCP gate, local free console, or enterprise hosted. No private protocol.
翻譯準備中
Daily Internet.nl standards measurements of a real fleet, made by the unmodified internetnl CLI against a self-hosted netnl facade.
翻譯準備中
Your agent knows a lot about you. Sanctuary keeps that information private. A firewall for your AI agent that runs on your own Mac, enforcing what it can reach at the operating-system level with keys
翻譯準備中
Self-hosted, metadata-only visibility and guardrails for the AI coding tools your engineers use. Never prompt text, never source code.
翻譯準備中
Verify once, access everywhere. KYC, KYB, and KYA compliance credentials via encrypted tokens and Interchain Messaging (ICM) on the Avalanche® blockchain. Non-custodial, software-only, no PII stored.
翻譯準備中
Local-first pentest agent: Go daemon + React dashboard + Codex/Claude Code/Pi runtimes, scoped projects, Blackboard, sandbox runners
翻譯準備中
Orca Security provides agentless, workload-deep, context-aware cloud infrastructure security and compliance through our comprehensive cloud security solution all in a single platform.
翻譯準備中
Verify Pakistani online stores and sellers before you pay, and file structured fraud disputes when something goes wrong. A free public database of reported scams, blacklisted brands, and dispute outco
翻譯準備中
Walletbeat is an Ethereum wallet rating site. It aims to provide a trustworthy, up-to-date source of information about the state of the Ethereum wallet ecosystem
翻譯準備中
Agents generate actions. rv authorizes them before they run. Hook-grade allow/deny for Grok, Pi, OpenCode, Claude, OpenClaw, Hermes, Codex, and Cursor.
翻譯準備中
Open-source security audit for your AI agents: the skills they run, exposed secrets, risky MCP config, and unsafe updates. Runs on your machine.
翻譯準備中
BitGraph allocates an unused position before it receives a file's SHA-256 fingerprint, then binds the fingerprint to that position and consumes it. The proof is a file you keep. It verifies offline.
翻譯準備中
Open-source cryptographic receipts, identity, and audit trails for AI agent sessions. Like TLS certificates, but for agents.
翻譯準備中
File transfer, datarooms and deposit boxes. End-to-end encrypted. Hosted in Europe.
翻譯準備中
ASCII-only by default, no escape parser, a paste warning and reveal modes, memory-safe. An opt-in TUI mode runs ssh, vim and htop, still filtering every character. Copy commands in and text out withou
翻譯準備中
Master prompts that turn any AI coding agent into a swarm of specialist auditors — evidence-bound, adversarially verified, filed as GitHub issues in German or English.
翻譯準備中
One compiled binary puts guardrails under the agent you already run: a destructive tool call is denied before it executes, every milestone needs a contract a human approved, and every execution leaves
翻譯準備中
Verified agent actions: authorization policy, signed receipts, and audit evidence for AI agent tool calls. One command to protect any MCP server.
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