#ai-security

Secure AI Engineering Framework 2026: Data-Boundary Security for Frontier Models

Sentinel shows what a file would make your AI coding agent do. Static analyzer, merge gate and signed lockfile for CLAUDE.md, AGENTS.md, .cursorrules, hooks and MCP configs.

Eight security skills for Claude Code with no dependencies: standard library only, tested, and usable as a CI step. Secret scanning, Python SAST, prompt-injection testing, plus HTTP, JWT, Dockerfile, CORS and dependency auditing.

Attack taxonomy, toolkit & defenses for persistent-memory poisoning of LLM agents. Author: Krishita Sanjay Choksi.

Prueba de seguridad, con Claude Code, a esa app que hiciste con IA. 20 fallas comunes, scanners gratis, prompts y blindaje.

Dual-track AI reference architecture: RAG system design & AI Security Engineering (EN/ZH) | 双轨 AI 参考架构：RAG 系统设计与 AI 安全工程

AI IR Overlay™ — practical incident response framework for AI agents in production. Built on NIST SP 800-61 r3, mapped to NIST AI RMF, NIST CSF 2.0, OWASP Top 10 for Agentic Applications 2026, ISO/IEC 42001, EU AI Act.

Offline repo inspection and change review for AI coding agents. Scan instructions, compare saved scans, explain findings, and export local reports.

Open-source Agentic AI Academy for engineering trustworthy AI agents from learning to production: agents, RAG, MCP, evaluation, security, observability, governance, enterprise architecture and production AI.

AI API key & subscription manager for Claude Code — your keys never touch the chat

Bounded Agents: Delegation Security for Multi-Agent AI Systems - Reference Implementation and Evaluation Artifact

Gateway-agnostic control plane for LLMs — an OpenAI-compatible governance proxy (auth, guardrails, budgets, routing, cost, observability) over a swappable engine: Bifrost / LiteLLM / Portkey / Direct. Own the control plane, swap the translator.

Self-hosted privacy firewall for LLM traffic. Detect, pseudonymize, route, and safely restore sensitive data through an OpenAI-compatible API.

Proxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.

A self-contained AI security lab demonstrating document poisoning, indirect prompt injection, and data exfiltration in RAG systems. Explores the "helpfulness paradox" across local and frontier LLMs.

Self-hosted pentest copilot. Substrate-first (technique catalog + playbooks + RAG + deterministic tools) with structural verifier rules and LLM-as-judge quality eval. Apache 2.0.

🛡️ AI Agent 远程审批系统 - 支持 Cursor/Trae/Claude Code/Codex 等 9 种 AI Agent，通过飞书推送审批卡片到手机/手表/PC，守护你的代码与文件安全

A practical 12-week Agentic AI learning roadmap covering LLM foundations, tool calling, RAG, memory, MCP, multi-agent systems, evaluation, security, and production deployment.

Save a secret: a small window opens that Claude cannot see, you paste there, it lands in 1Password. Read it back: any item in your vault loads into Claude with one fingerprint check, names only, never the values. Keys you paste in the chat are deleted before Claude reads them. Mac, Windows, Linux. MIT.

Border Guard — AI-native territory sovereignty & self-evolving security OS. 6-module D-S fusion engine, trajectory detection, anchor detection, fission engine, territory adjudicator. Full design + Python implementation.

Tamper-evident audit logging for OpenClaw and other local AI agents: hash-chained, locally verifiable, zero cloud dependency.

AI Guardian Firewall — a local, user-space, agent-agnostic firewall that mediates an autonomous AI agent's actions (files, shell, network, services) with a deterministic policy boundary, a tamper-evident audit log, and a human-in-the-loop approval cockpit. No kernel modules. Apache-2.0.

A carnivorous honeypot for autonomous AI agents. Sweet-looking bait. Sticky ending.

Memory integrity for AI agents — Information-flow control against OWASP ASI06 memory & context poisoning.

Open-source AI Security Gateway that sanitizes secrets, PII, and internal context before prompts reach external LLMs.

Defensive security audit skills for Claude — tech-stack-keyed and audit-domain-keyed packs for SaaS apps.

A cybersecurity-focused research project analyzing the current state of AI, emerging AI-enabled threats, and practical defensive controls.

Claude Code scaffold for building AI platforms securely — agent/LLM security, Kubernetes, SRE, observability, identity, and supply chain, grounded in published framework canon (OWASP, NIST, CIS, SLSA). Data-science lanes included.

Runtime security gateway that stops AI agents from being tricked into leaking data — taint tracking + policy enforcement to contain the lethal trifecta.

Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.

Evidence-driven GPT-5.5 relay MITM audit console for canaries, prompt injection, tool calls, and usage anomalies.

Agent context gate for Codex, Claude Code, Copilot, MCP, Cursor, Cline, Gemini and Windsurf repos

v0.8 preview · 2,288 multi-step agent trajectories · 513 hand-authored gold + 1,775 provenance-flagged augmented. A per-step benchmark that scores whether a verifier catches drift inside an agent's trajectory — not whether a prompt is harmful.

TokenFuse — runtime control for AI agents: per-run budgets, loop detection, burn forecast, kill-switch. Observability shows the fire; TokenFuse is the automatic extinguisher.

Real-time scam-detection Discord bot — a Gemini analyst flags 11 manipulation tactics per message, then auto-warns, mutes, and alerts moderators in one message event. TypeScript monorepo.

AI security layer for the agentic internet — sandbox isolation, Civic governance, and a one-API-call clearance system for any OKX.AI agent.

AI 中转站 API 验真取证工具：模型验真 · 系统提示词提取 · 上下游供应链溯源 | LLM relay API forensics: verify models, extract system prompts, trace upstream supply chains

ai security cli developer-tools agent firewall policy-as-code python anthropic claude-code

Autonomous multi-agent AI penetration testing framework — 20 specialist agents, ECC architecture, MITRE ATT&CK + OWASP mapped, HMAC-chained audit trail, Docker sandbox, and multi-LLM backend (Ollama/OpenAI/Anthropic).

Unlock AI Coding with OpenCode Local Provider 2026 - Auto-Detect Ollama LM Studio