#LayerX
東銀座のLayerX社で登壇した帰り道です
June 12, 2025 at 1:36 PM
ITmedia 総合記事一覧: [ITmedia ビジネスオンライン] 月30万円かかるAIは「学習しない社員」だった――LayerXが回し始めた仕事の“自己改善ループ”
[ITmedia ビジネスオンライン] 月30万円かかるAIは「学習しない社員」だった――LayerXが回し始めた仕事の“自己改善ループ”
ITmedia 総合記事一覧
www.itmedia.co.jp
September 25, 2026 at 12:20 AM
🚨 Warning: Perplexity’s Comet Browser 🚨

Researchers from LayerX Security have revealed that the browser is vulnerable to CometJacking attacks, allowing hackers to hijack sessions & access data.

More: tuta.com/blog/perplex...
October 25, 2025 at 12:53 PM
“BioShocking” tricks #AI browsers into leaking your passwords - thenextweb.com/news/bioshoc... "convinced six AI browsers, including ChatGPT Atlas, Perplexity’s Comet, and Anthropic’s Claude, that stealing your credentials was just the next level of a puzzle. Most of them still fall for it. " great
‘BioShocking’ tricks AI browsers into leaking passwords
LayerX tricked six AI browsers, including ChatGPT Atlas, Comet and Claude, into leaking user credentials by convincing them they were playing a game.
thenextweb.com
July 2, 2026 at 9:09 AM
naoyaさん山口さんと行ったパネルディスカッションが動画になりました。地に足のついた話、あるいは夢のない話をしています。何卒よろしくお願いします!

【t-wadaさん, 一休CTO, LayerX】AI時代の開発スピードと品質 / 本当の意味で開発生産性を上げるために必要なこと
www.youtube.com/watch?v=MhPA...
【t-wadaさん, 一休CTO, LayerX】AI時代の開発スピードと品質 / 本当の意味で開発生産性を上げるために必要なこと
YouTube video by TECH WORLD
www.youtube.com
November 15, 2025 at 2:46 AM
今日からLayerXで働いてやす
(タイポってたので再投稿)
August 1, 2025 at 12:56 PM
"The zero-click remote code execution (RCE) flaw in Claude Desktop Extensions (DXT) allows attackers to compromise a system using nothing more than a maliciously crafted Google Calendar event."
Claude Desktop Extensions 0-Click RCE Vulnerability Exposes 10,000+ Users to Remote Attacks
A new critical vulnerability discovered by security research firm LayerX has exposed a fundamental architectural flaw in how Large Language Models (LLMs) handle trust boundaries.
cybersecuritynews.com
February 13, 2026 at 11:22 PM
This Japanese AI startup just raised $100M to cut businesses’ admin burden.
LayerX uses AI to cut enterprise back-office workload, scores $100M in Series B | TechCrunch
This Japanese AI startup just raised $100M to cut businesses’ admin burden.
techcrunch.com
September 1, 2025 at 11:02 PM
更新系と状態
2025-04-23 Exploring State - LayerX Web Frontend Night
speakerdeck.com
April 23, 2025 at 12:47 PM
So the Claude extension allows any other extension to inject JavaScript into claude.ai and run it? Cool cool cool.

Yeah, don't let this one in.
ClaudeBleed: A Flaw In Claude's Browser Extension Allows Any Extension to Hijack It - LayerX
Executive Summary LayerX security researchers have discovered a flaw with Claude’s Chrome extension (“Claude in Chrome”) that allows any extension, even one with no special permissions at all, to effectively hijack Claude’s extension by injecting it with malicious instructions, extract any information that the attacker desires, and get Claude to perform active agentic actions on […]
layerxsecurity.com
May 8, 2026 at 1:22 PM
This one is novel! Instead of a more classic indirect prompt injection, this CSRF attack (against ChatGPT itself) injects malicious instructions into the "Memory" layer of the ChatGPT app, so that future prompts are poisoned by that additional context.
“ChatGPT Tainted Memories:” LayerX Discovers The First Vulnerability in OpenAI Atlas Browser, Allowing Injection of Malicious Instructions into ChatGPT - LayerX
  LayerX discovered the first vulnerability impacting OpenAI’s new ChatGPT Atlas browser, allowing bad actors to inject malicious instructions into ChatGPT’s “memory” and execute remote code. This exploit can allow attackers to infect systems with malicious code, grant themselves access privileges, or deploy malware. The vulnerability affects ChatGPT users on any browser, but it is […]
layerxsecurity.com
October 27, 2025 at 1:31 PM
tech.layerx.co.jp/entry/20...
フロントエンドカンファレンス福岡2026に参加しました #fec_fukuoka - LayerX エンジニアブログ
フロントエンドカンファレンス福岡2026に参加しました #fec_fukuoka - LayerX エンジニアブログ
tech.layerx.co.jp
September 22, 2026 at 4:56 PM
ninjinkunさんもlayerXなんだ…!
March 31, 2026 at 8:31 PM
LayerX says it received no clear response after it flagged a serious #ClaudeCode flaw to Anthropic that bypasses safety rules, letting attackers run SQL injection and steal credentials using simple instructions.

Read: hackread.com/claude-code-...

#CyberSecurity #Claude #Anthropic #AI #LayerX
Claude Code overview - Claude Code Docs
Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.
CLAUDE.md
April 9, 2026 at 2:06 PM
Chrome extension devs are blatantly selling your data and not even hiding it anymore because nobody reads the ToS these days

layerxsecurity.com/blog/your-ex...
Extension Developers Sell The Data of At Least 6.5 Million Users - And It’s All Completely Legal - LayerX
Your Extensions Sell Your Data - And It's Perfectly Legal
layerxsecurity.com
April 28, 2026 at 11:39 AM
インボイス制度の経済損失は年間4兆円ってマジなの・・・

10月以降「インボイス残業」発生へ 人件費「全国で月3400億円分」増加か LayerX試算
www.itmedia.co.jp/news/spv/230...
September 20, 2023 at 11:09 PM
-New Kimsuky malware paleontology report
-New Apache Tomcat RCE
-New NGINX Rift vulnerability
-MCP server bugs
-Cisco lays off 5% of staff
-Akamai buys LayerX
-Microsoft releases AntiSSRF
-New Vulnerability.Garden tool
May 15, 2026 at 8:31 AM
機能を作るな。楽して作るな。 (LayerX社内資料) Don’t Build Features. Don’t Take the Easy Way Out.
https://speakerdeck.com/mosa_siru/don-t-build-features-dot-don-t-take-the-easy-way-out
機能を作るな。楽して作るな。 (LayerX社内資料) Don’t Build Features. Don’t Take the Easy Way Out.
LayerX社内の定例でつかった資料です。
speakerdeck.com
June 15, 2026 at 7:20 AM
“ChatGPT Tainted Memories:” LayerX Discovers The First Vulnerability in OpenAI Atlas Browser, Allowing Injection of Malicious Instructions into ChatGPT

layerxsecurity.com/blog/layerx-...

#CyberSecurity #ChatGPT #OpenAI #AtlasBrowser
“ChatGPT Tainted Memories:” LayerX Discovers The First Vulnerability in OpenAI Atlas Browser, Allowing Injection of Malicious Instructions into ChatGPT - LayerX
LayerX discovered the first vulnerability impacting OpenAI’s new ChatGPT Atlas browser, allowing bad actors to inject malicious instructions into ChatGPT’s “memory” and execute remote code. This explo...
layerxsecurity.com
November 4, 2025 at 9:12 AM