# Blog and articles by Liran Tal

Blog posts and selected articles on AI security, Node.js, developer tooling, and secure coding, across lirantal.com, Node.js Security, Snyk, and guest publications including Tessl and Infosecurity Magazine.

Canonical: https://lirantal.com/writing

## Search Liran Tal's writing

Search published article titles, summaries, categories, and tags. Browser agents can use this search through WebMCP when supported.

Search topics  Search articles

Lirantal.com

## Recent blog posts.

[Complete blog archive](/blog) [Subscribe via RSS](/rss.xml)

 [![](/_astro/self-host-hermes-agent-matrix-e2ee-proxmox.D6XUPjt5_Ua06g.png)

Sep 5, 2026

### Self-Hosting Hermes Agent with Matrix E2EE on Proxmox

Build a private, mobile-first Hermes Agent using Matrix Synapse, Element, end-to-end encryption, Tailscale Serve, and separate Proxmox LXC containers.](/blog/self-host-hermes-agent-matrix-e2ee-proxmox)

 [![](/_astro/practical-second-brain-llm-markdown-knowledge-graph.CEcxBkpJ_Z19xT21.png)

Aug 2, 2026

### The Practical Second Brain: Building an LLM-Operated Markdown Knowledge Graph

A hands-on guide to the files, schemas, workflows, governance, and maintenance routines behind an AI-assisted second brain.](/blog/practical-second-brain-llm-markdown-knowledge-graph)

 [![](/_astro/building-second-brain-llms-ai-agents.B3w2y6mA_2fR1l0.png)

Aug 1, 2026

### Building a Second Brain with LLMs and AI Agents

How a plain-Markdown knowledge graph becomes a durable context layer, operating system, and compounding productivity tool for AI-assisted work.](/blog/building-second-brain-llms-ai-agents)

 [![](/_astro/gemini-cli-invisible-unicode-skill-injection.AW0ivLkB_Z2nFK4g.png)

Jul 17, 2026

### Invisible Unicode Can Hijack Gemini CLI Agent Skills

I disclosed a Gemini CLI prompt injection where invisible Unicode tag characters in SKILL.md caused the agent to run a hidden command. Google closed the report as out of scope because the workspace was trusted and YOLO mode was enabled.](/blog/gemini-cli-invisible-unicode-skill-injection)

 [![](/_astro/build-agent-workflows-around-state-ownership.BjADEWUr_23EDIL.png)

Jul 2, 2026

### Build Agent Workflows Around State Ownership, Not Timing

A practical pattern for turning a fragile Codex state migration into a reusable skill with backups, process ownership, validation, and a terminal helper.](/blog/build-agent-workflows-around-state-ownership)

 [![](/_astro/portable-terminal-dotfiles-chezmoi.CIGhyhT9_2erb6U.png)

Jun 30, 2026

### How to Turn a Custom Terminal Setup into Portable Dotfiles with chezmoi

A practical guide to turning a custom macOS terminal setup into portable, reviewable dotfiles with chezmoi, Homebrew Bundle, zsh modules, Starship, and a public-safe repository workflow.](/blog/portable-terminal-dotfiles-chezmoi)

 [![](/_astro/devrel-2026-thematic-shifts-product-centric-advocacy-coding-agents.DqDULCVh_11jcBs.jpg)

Jun 18, 2026

### DevRel in 2026: Thematic Shifts, Product-centric Advocacy and the Rising Tide of Coding Agents

Explore DevRel in 2026: how coding agents, AI builders, X-first communities, DevRel engineering, and product-centric advocacy are reshaping the field.](/blog/devrel-2026-thematic-shifts-product-centric-advocacy-coding-agents)

 [![](/_astro/coding-agents-do-not-replace-technical-proficiency.jTwhgEmj_XAayt.png)

May 10, 2026

### Coding Agents Do Not Replace Technical Proficiency — They Demand More of It

LLMs and coding agents amplify developer capability but they do not substitute for it. Engineering experience determines whether you steer these tools toward sound architecture or blindly accept generated output that drifts from your conventions.](/blog/coding-agents-do-not-replace-technical-proficiency)

## Here on lirantal.com

Research write-ups, developer tools, and things I learn along the way.

[Browse the blog](/blog)

## Node.js Security

Vulnerability deep dives and practical secure coding for JavaScript developers.

[Read Node.js Security](https://www.nodejs-security.com/blog)

## Snyk

Articles and research on AI security, application security, and the software supply chain.

[Browse my Snyk articles](https://snyk.io/contributors/liran-tal/)

Selected articles

## Published elsewhere.

Tessl · Guest article

October 8, 2026

### [Agent Skills Are Supply Chain Components](https://tessl.io/blog/agent-skills-are-supply-chain-components)

Why reusable agent skills need provenance, review, scanning, and the security discipline of software supply chains.

Snyk Articles

January 2026

### [Building Secure MCP Servers: A Developer’s Guide to Avoiding Critical Vulnerabilities](https://snyk.io/articles/building-secure-mcp-servers/)

Command injection, path traversal, and the pitfalls of read-only database access in MCP servers.

Tessl · Guest article

December 10, 2025

### [These Aren't the Tools You're Looking For: The Hidden Dangers of MCP](https://tessl.io/blog/these-aren-t-the-tools-you-re-looking-for-the-hidden-dangers-of-mcp)

MCP security risks spanning toxic data flows, tool poisoning, and classic code vulnerabilities.

Node.js Security

November 2025

### [Argument Injection vulnerability in git-blame@1.4.0](https://www.nodejs-security.com/blog/argument-injection-vulnerability-in-git-blame-1-4-0)

How an unsanitized revision parameter becomes a command execution risk in a Git wrapper.

Snyk Blog

July 2025

### [Cursor IDE Malware Extension Compromise in $500k Crypto Heist](https://snyk.io/blog/cursor-ide-malware-extension-compromise-in-usd500k-crypto-heist/)

A look at malicious extensions and the trust developers place in their tools.

Infosecurity Magazine · Guest opinion

December 2, 2021

### [Securing the Modern Software Supply Chain](https://www.infosecurity-magazine.com/opinions/securing-the-modern-software/)

Practical defenses for software supply chains, including dependency confusion, package installation scripts, registry authentication, and protecting sensitive information.