#ai-security

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

Production-ready Claude Code skills for cybersecurity — secret scanning, SAST, prompt-injection testing, HTTP/JWT/dependency auditing. Zero dependencies.

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

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.

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

🛡️ 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

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

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.

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

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.

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

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

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

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

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

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).

Curated research on AI agent social engineering, manipulated delegation, prompt injection, tool-use boundaries, and agent security evaluation.

Source-backed archive of agent prompt-injection incidents, research records, trust-boundary patterns, schemas, and sanitized defensive summaries.

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

Free AI-agent risk self-check, security checklist, and USD 59 launch-readiness mini-audit offer.

Validates AI artifacts for security, performance, quality, compliance, and operational risks before peer sharing. It implements a risk framework covering 198 risks across 14 artifact types and 14 scanner modules, including dynamic runtime analysis of live MCP servers.

A foresight and learning repository for translating early AI, cybersecurity and technical signals into strategic relevance for organisations, governance and adoption.

Synthetic Splunk-native dataset and detection prototype for AI-agent monitoring-control-plane tampering

Privacy-first Chrome extension and Flask backend for protecting AI prompts through real-time PII detection, anonymization, pseudonymization, and redaction before sensitive data reaches AI services.

Official desktop companion for tragentics.com — encrypted local vault for agent tokens plus a heartbeat engine that keeps your registered agents online. Windows, macOS, and Linux.

An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a poisoned input contaminated. Built on substrate.

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

Live DSPM Posture Simulator — Azure AI agent data exposure risk assessment (educational tool).

MonkeyCode 2026: AI Dev Platform with Cloud IDE & Top LLMs - Open Source

A JSON-RPC firewall for MCP agents — inspects every tools/call between an LLM and its MCP servers, blocking argument injection and capability creep before they reach the host.

Unified open-source security shield for agentic AI systems — defense-in-depth prompt-injection protection (canary tokens, agent-trace alignment audit, tool-call guarding, PII/secret scanning).

Local-first security release checker for authorized code, AI apps, freelancers, and small teams

Ryan Prasad's AI Engineering portfolio and recruiter-agent GitHub profile README