#JWT security
74 related articles
·7 min
In-Depth Analysis of the GitLost Vulnerability: How GitHub AI Agents Were Tricked into Leaking Private Repositories
Security researchers disclose the GitLost attack, which uses prompt injection to trick GitHub AI agents into leaking private repository source code. An in-depth analysis of the attack principle, AI agent security risks, and developer defense recommendations.
Read more →
·7 min
Connecting Hermes Agent to MCP: One Protocol to Unify All External Systems
Learn how to extend Hermes Agent's external system capabilities via MCP (Model Context Protocol): setup, whitelist permissions, WSL-to-Chrome bridging, and multi-server orchestration for AI Agent developers.
Read more →
·6 min
Semi-AI Mode: A Practical Guide to Implementing API Automation Testing
Can't make pure AI work? This guide explores the Semi-AI approach to API automation testing, covering key challenges, enterprise framework design, and how AI and frameworks work together for maximum impact.
Read more →
·6 min
AI Workspace Session and Cache Leaks: A Complete Analysis of Multi-Tenant Isolation Security Risks
AI workspaces face cross-tenant session and cache leak risks that can expose sensitive enterprise data. This article analyzes multi-tenant isolation pitfalls, common architectural flaws, and actionable defenses.
Read more →
·2 min
MCP Protocol Deep Dive: The Unified Standard and Practical Guide for Agent Development
Deep dive into MCP (Model Context Protocol): core principles, communication mechanisms, and security design. Learn how MCP replaces Function Calling and enables remote agent-tool integration.
Read more →
·7 min
AI Agent Development: A Four-Stage Competency Model from 15K to 40K RMB Salary Growth Path
A detailed four-stage competency model for AI Agent development: from Python/RAG basics (15K) to workflow orchestration (20K), inference optimization (30K), and Agent cluster governance (40K RMB).
Read more →
·7 min
Cloudflare Natively Supports the x402 Protocol: How Micropayments Are Reshaping Web Monetization
Cloudflare announces native x402 HTTP payment protocol support, enabling developers to charge stablecoin micropayments for API calls without accounts or keys. Deep dive into how x402 works and its impact on AI Agent economics.
Read more →
·4 min
AI Agent Memory System Architecture Breakdown: A Practical Selection Guide from 16 Open-Source Projects
Deep analysis of memory system architectures across 16 open-source AI Agent projects including Hermes, Goose, NanoClaw, and Deerflow, covering FTS5 vs vector search, multi-tenant isolation, and LLM auto-extraction.
Read more →
·3 min
OpenAI Codex Fully Explained: The Paradigm Shift from ChatGPT Conversations to Autonomous AI Programming
Deep dive into OpenAI Codex vs ChatGPT: ChatGPT explains, Codex executes. Learn how AI programming agents autonomously generate code, fix bugs, and run tests.
Read more →
·3 min
AI Programming: Can You Really Build Apps Without Coding? An In-Depth Analysis of Real Capabilities and Monetization Paths
Can AI programming tools really let non-coders build and monetize apps? This article analyzes AI coding's true capabilities, viable monetization paths, and common misconceptions.
Read more →
·2 min
Devin Review Security Audit Feature Explained: How AI Code Review Detects Deep Security Vulnerabilities
Devin Review adds AI security audit to auto-detect auth bypasses, logic flaws & deep vulnerabilities in every PR, with full remediation from finding to fix.
Read more →
·3 min
Trae Hands-On Tutorial: Build a Full-Stack Website with Just 3 Prompts
Learn how to use ByteDance's AI coding tool Trae to build a full-stack website with just 3 prompts—covering frontend, backend API, and admin panel.
Read more →
·3 min
How to Polish AI-Generated Auth Systems to Production-Ready Quality
Learn how to polish Copilot-generated Auth systems from error-prone drafts to production-ready code, covering bug fixes, i18n replacement, and effective AI collaboration tips.
Read more →
·3 min
Claude-mem: The Open-Source Memory System That Stops AI from Forgetting
Claude-mem is an open-source AI memory tool that gives Claude Code, Codex, and other AI coding assistants cross-session memory via semantic compression and vector retrieval — just 50 tokens of overhead, fully local storage.
Read more →
·4 min
Building a Personal Blog from Scratch with Cursor: A Complete AI-Powered Development Tutorial
Learn how to build a personal blog from scratch using Cursor AI — covering UI prototyping, full-stack code generation, database setup, and bug debugging with almost no hand-written code.
Read more →
·3 min
Reading Code Is More Important Than Writing It in the AI Era: 6 Practical Tips to Improve Your Code Reading Skills
In the age of AI-generated code, reading code is a critical skill. Learn 6 practical techniques—from entry point reading to tracing data flows—using a login endpoint example.
Read more →
·4 min
Cursor Deep Dive: Core Advantages and Use Cases of an AI-Native Programming Tool
Deep dive into Cursor's four core features, six-dimension comparison with traditional IDEs, and analysis of target users. Learn how this AI-native code editor redefines programming through natural language interaction.
Read more →
·1 min
MCP Protocol Explained: The Unified Standard for AI Agent-Tool Communication
Deep dive into MCP (Model Context Protocol): architecture, communication mechanisms, security, and how it differs from Function Calling as the new standard for AI agent-tool communication.
Read more →
·2 min
Tsinghua and Zhipu Release Full-Stack Web Dev Benchmark: Top AI Models Fail Spectacularly
Tsinghua and Zhipu AI release a full-stack web dev benchmark with three difficulty levels. Top models like Gemini 2.5 Pro see scores plummet from 63 to 11.7 on full-stack tasks, exposing AI's real limits.
Read more →
·3 min
NestJS + LangChain: A Practical Guide for Frontend Engineers Transitioning to AI Full-Stack Architecture
How can frontend engineers transition to AI full-stack? This guide covers NestJS + LangChain, TypeScript fundamentals, AI Agent development, local model deployment, and cross-language architecture skills.
Read more →