Anthropic-Credited-CVEs

ANTHROPIC CVE TRACKER Overview Tracking vulnerabilities that credit the Anthropic research team and are possibly discovered by Project Glasswing. CURRENT CVE COUNT: 149 Initial Research Tracking CVEs Attributed to Anthropic Researchers and Project Glasswing Add a Vulnerability If you find an...

synaptic-sentinel

SYNAPTIC Sentinel バイブコーディングのセキュリティセンチネル。 Apache-2.0ライセンスのエージェンティックセキュリティツールキットで、コードの大部分がAIによって書かれるプロジェクト向け。5つの決定論的スカウトが構文上の問題を検出し、Brain Layer（BYOK Anthropic）が本当に重要な問題とその修正方法を判断します。すべてIDE内で動作します。 SYNAPTIC Sentinel は、プロジェクトをクライアントの境界内...

Anthropic-Cybersecurity-Skills

Anthropic Cybersecurity Skills AIエージェント向け、最大のオープンソースサイバーセキュリティスキルライブラリ !Hermes Agenthttps://img.shields.io/badge/HermesAgent-compa...

defending-code-reference-harness

Defending Code Reference Harness Claude Mythos Preview のリリース以降、複数の組織のセキュリティチームとの協業から得た知見に基づく、Claude を用いた自律的な脆弱性発見と修正のためのリファレンス実装です。これらの知見とベストプラクティスについては、付随するブログ記事（blog-post.md でも入手可能）を参照してください。同じ recon → find → triage → report → patch ループの軽量な SDK のみのウォークスルーについては、コンパニオンクックブックを参照してください。...

vLLM <= 0.23.0 - Anthropic Router Heap Address Information Leak

vLLM = 0.23.0 incompletely fixes CVE-2026-22778. The original fix added sanitizemessage to the OpenAI router but the Anthropic-compatible router /v1/messages echoes strexc directly. id: CVE-2026-54236 info: name: vLLM = 0.23.0 - Anthropic Router Heap Address Information Leak author: kenlacroix...

MCP Inspector < 0.14.0 UnauthenticatedRemote Code Execution

The MCP inspector is a developer tool for testing and debugging MCP servers. Versions of MCP Inspector below 0.14.1 are vulnerable to remote code execution due to lack of authentication between the Inspector client and proxy, allowing unauthenticated requests to launch MCP commands over stdio. id...

CVE-2026-21852-PoC

Claude Code 脆弱性教育デモ このプロジェクトは、Check Point Research が公開した Anthropic の Claude Code CLI における3つの脆弱性を実演するものです。サイバーセキュリティを学ぶ学生や研究者が、AI開発ツールのサプライチェーン攻撃がどのように機能するかを理解するために設計されています。 対象脆弱性...

cve-2025-65099

CVE-2025-65099 の概念実証 詳細は公開記事をご参照ください。 yarnPath テクニック yarnPath 用の脆弱な環境は以下のように初期化できます。 root@kitploit: docker run --rm -v "$PWD":/poc -it --workdir /poc ubuntu bash -c 'apt-get update -qq && DEBIANFRONTEND=noninteractive apt-get install npm -y -qq && npm install -g yarn && npm install -g...

CVE-2025-54794-Hijacking-Claude-AI-with-a-Prompt-Injection-The-Jailbreak-That-Talked-Back

🧠 CVE-2025-54794: Claude AIをプロンプトインジェクションで乗っ取る – 逆切れした脱獄 By Aditya Bhatt | オフェンシブセキュリティスペシャリスト | レッドチームオペレーター | VAPT中毒者 ⚔️ はじめに: AIが言葉でハックされる時代 言語モデルがコード、コンテンツ、思考の副操縦士となった現代、脆弱性はもはやポートやペイロードだけの話ではありません。それは言葉 の問題なのです。 CVE-2025-54794 は、CVEアーカイブの中の単なる番号ではありません。それは次のような声明です。 「最も先進的なAIでも、適切なささやきで操作されうる...

Anthropic Says Seven China-Based AI Labs Ran Industrial-Scale Claude Distillation Attacks

Anthropic on Thursday said it identified and disrupted industrial-scale illicit distillation attacks against Claude from seven labs based in China, including Alibaba, Moonshot, DeepSeek, Z.ai aka Zhipu, and MiniMax. Knowledge distillation by itself is a legitimate training method. It refers to a...

Nobody Is Saying Why OpenAI and Anthropic Had Outages Today

ChatGPT, Claude, and Grok all suffered outages at nearly the exact same time for reasons that remain murky...

aiagent-detection-rules

aiagent-detection-rules Sigma-, Splunk-, Elastic- und YARA-Erkennungsregeln für den Claude-Code-Quellcode-Leak 31. März 2026 und den gleichzeitigen npm-Lieferkettenangriff. Am 31. März 2026 hat Anthropic versehentlich eine fehlkonfigurierte Source-Map in @anthropic-ai/[email protected]...

AI "Mind Viruses" Can Spread Between Agents Through Persistent Prompt Files

Security researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads can spread from one artificial intelligence AI agent to the next through the editable system prompt files that autonomous agent harnesses use to carry state between sessions. The work, releas...

If the Markets Reject OpenAI and Anthropic, the US Should Nationalize Them

This essay was written with Nathan E. Sanders, and originally appeared inThe Guardian. OpenAI, and then Anthropic, were each formed by AI developers who feared unrestrained corporate AI development--specifically, that companies like Google and Meta would steer the technology towards deleterious,...

OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning

A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords. The weakness affected encrypted reasoning objects used by the providers'...

MAL-2026-13414 Malicious code in @atom8n/inspector (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5b72c3643bb990395103d396d62440db908b84769c904d4c14aa9b259f97807c This @atom8n/-scoped package impersonates Anthropic's official MCP inspector package.json declares author 'Anthropic, PBC' and homepage...

Poison Claude Sells Discounted Claude Access While Its Operator Sees Every Customer Prompt

Cybersecurity researchers have discovered more than half-a-dozen services advertisements for illegal access to artificial intelligence AI models on underground cybercrime forums and messaging platforms. One such service, Poison Claude, claims to offer access to Anthropic's large language models...

Malicious code in anthropic-setup (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector baee404f50ce2f767660b7f6cf21dec0df6b0d0da68b9bc39ce506f941f1f664 The package is presented as an Anthropic API setup helper npx anthropic-setup sk-ant-.... When invoked, it writes /.claude/settings.json with...

MAL-2026-12510 Malicious code in anthropic-setup (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector baee404f50ce2f767660b7f6cf21dec0df6b0d0da68b9bc39ce506f941f1f664 The package is presented as an Anthropic API setup helper npx anthropic-setup sk-ant-.... When invoked, it writes /.claude/settings.json with...

Malicious code in sextant-cli-linux-arm64 (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector fc34f69b5a68c549feccfb32cc2dbfbf2d4c787a4876241027b4299305fd2c53 The package is a platform-specific leaf linux/arm64 whose only shipped artifact is a 12 MB stripped Go binary at bin/sxt. The package.json omits...