gryffin

ARCHIVED Gryffin beta Gryffin is a large scale web security scanning platform. It is not yet another scanner. It was written to solve two specific problems with existing scanners: coverage and scale. Better coverage translates to fewer false negatives. Inherent scalability translates to capabilit...

SecureML

SecureAIML 🔐 OpenSSF Model Signing に基づくエンタープライズ対応 AI モデルセキュリティ SecureAIMLは「モデルセキュリティのStripe」です。エンタープライズグレードのAIモデル保護を、あらゆる組織にとってアクセスしやすく、使いやすく、本番運用可能なものにします。 SecureAIMLが選ばれる理由 AI/MLの時代において、モデルセキュリティは極めて重要です。SecureAIMLは、強力な OpenSSF Model Signing 標準を、直感的でエンタープライズ対応のインターフェースで包み込み、MLモデルの保護を次のように簡単にします...

CVE-2025-51471-POC

CVE-2025-51471 - Ollama 교차 도메인 토큰 노출 PoC 작성자: ajtazer 🔥 개요 이 저장소는 Ollama의 모든 버전최신 버전 포함에 영향을 미치는 교차 도메인 인증 토큰 노출 취약점인 CVE-2025-51471 에 대한 개념 증명PoC을 포함합니다. 📋 취약점 설명 Ollama가 401 Unauthorized로 응답하는 HTTPS 서버에서 모델을 가져올 때, WWW-Authenticate 헤더의 realm URL을 동일한 도메인에 속하는지 검증하지 않고 따릅니다... 이를 통해 공격자는 다음을 수행할...

moc3ingbird

Future Work 이 공간에서의 향후 작업은Sakura Motion 조직 아래에서 이루어지며, 우리의 Core 재작성: https://github.com/SakuraMotion/PurismCore로 시작됩니다. MOC3ingbird DoS 日本語版：READMEJA.md 이 저장소는 로드하려는 모든 애플리케이션을 충돌시키는 간단한 Live2D 모델을 포함하고 있습니다: 서비스 거부 공격. ImHex hex editor가 설치되어 있다면, src/moc3.hexpat 패턴 파일을 사용하여 MOC3 파일을 검사하고 편집할 수...

GuardModel

GuardModel YAML 한 줄로 파이프라인의 악성 AI 모델을 차단하세요. GuardModel은 CI/CD 파이프라인에서 ML 모델 파일을 자동으로 스캔하여 악성 코드, 취약점, 보안 위험을 탐지하는 GitHub Action입니다. pickle 역직렬화 공격, 포함된 악성코드, 알려진 CVE를 탐지하여 위험한 모델이 프로덕션에 도달하기 전에 차단합니다. 빠른 시작 워크플로우에 추가하세요: name: GuardModel Security Scan on: push, pullrequest jobs: scan: runs-on:...

Security Bulletin: HttpClient based on the classic i/o model fails to correctly release the underlying connection

Summary HttpClient based on the classic i/o model fails to correctly release the underlying connection back to the connection manager if it encounters an invalid or unsupported Content-Encoding header value in the response message. Please note this defect does not affect HttpClient based on the...

BrokenHill

!\ Broken Hill logo \https://assets.kitploit.com/production/public/readmes/44608/c14154675c6f33f5c3887887afcdb39351c82f269ee2772cf31847106a20a871.jpg Broken Hill Broken Hill은 대규모 언어 모델LLM의 제한을 우회하도록 제작된 프롬프트를 생성하는, 프로덕션 수준에서 바로 사용 가능한 자동화 공격 도구입니다. Andy Zou, Zifan Wang, Nicholas Carlini, Milad...

AI_Security_Top

🛡️ AI-Security-Knowledge-Base これは体系的な AI セキュリティ研究プロジェクトであり、基礎的な機械学習アルゴリズム理論から最先端の大規模言語モデル注入攻撃、AI 検知回避（免杀）対策、ディープフェイク（Deepfake）に至るまでの完全な知識体系を網羅しています。 🏗️ 知識体系アーキテクチャ 本リポジトリの内容は、AI コアアルゴリズム 、脅威モデリング 、レッドチーム攻撃 、ブルーチーム防御 の4つの主要セクションに分かれています。 🧬 一：AI の基礎と理論...

org.apache.httpcomponents.client5/httpclient5: Apache HttpComponents Client: Denial of Service due to connection leak

A flaw was found in Apache HttpComponents Client, specifically in its classic input/output I/O model. When processing a response message with an invalid or unsupported Content-Encoding header, the client fails to properly release the underlying network connection. This connection leak can lead to...

Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context

Summary Decepticon wraps web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK Bring Your Own Key deployment model, users configure their own LLM credentials to any OpenAI-compatible...

binviz

binviz バイナリ可視化＆トリアージツール：単一の共有アドレス空間モデル上で、リンクされた対話型ビュー（エントロピー、ヒストグラム、画像/ドットプロットサーフェス、制御フローグラフ）を提供します。 pipx install binviz && binviz serve 機能概要 ファイルを開くと、すべてのビューが同じアドレス空間を参照します。1つのビューで範囲を選択すると、他のビューも連動します — 目的は「この領域は何か」という問いに、複数の視点から同時に答えることです。 マッピング。 binviz model は LIEF を通じて ELF/PE/Mach-O...

CVE-2026-61732

Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK Bring Your Own Key deployment model, users...

CVE-2026-34940

CVE-2026-34940 — OS Command Injection in KubeAI via Model URL in Ollama startup probe Severity : High CVSS 8.7 CWE : CWE-78 — Improper Neutralization of Special Elements used in an OS Command Affected : github.com/kubeai-project/kubeai = 0.23.1 Fixed in : 0.23.2 Advisory : GHSA-324q-cwx9-7crr NVD...

CVE-2026-22807_Range

🛡️ CVE-2026-22807 シミュレーション: AI サプライチェーン RCE ターゲットレンジ ⚠️ 免責事項 / Disclaimer 本プロジェクトはセキュリティ研究および教育目的 のみに使用され、AI モデル読み込みプロセスにおけるサプライチェーン攻撃の原理（Remote Code Execution）をデモンストレーションすることを目的としています。 本番環境で生成された悪意のあるモデルを使用しないでください。また、本プロジェクトを違法な攻撃行為に使用することは固く禁じられています。開発者は、不適切な使用によって生じたいかなる法的責任も負いません。 📖 プロジェクト概要...

tesseract: Tesseract: Heap out-of-bounds write via crafted .traineddata

A flaw was found in Tesseract, an open-source Optical Character Recognition OCR engine. A remote attacker could exploit this by providing a specially crafted .traineddata LSTM model component. When Tesseract's deserializer processes this component during OCR recognition, an unchecked integer...

9router: Image prefetch DNS rebinding allows SSRF to internal services

Summary 9router validates image URLs by resolving the host before fetching, but the later server-side fetch performs a separate DNS resolution. An attacker-controlled DNS name can resolve to a public IP during validation and then rebind to an internal Docker/private IP during the fetch. This allo...

CVE-2026-71461

HostList.list catches bare Exception and returns stre verbatim. Via hostfilter, any authenticated user triggers Django FieldError leaking complete Host model relation graph including internal reverse accessors or PostgreSQL DataError leaking raw database error strings. Two primitives:...

Important: Red Hat Security Advisory: Red Hat AI Inference Model Optimization Tools 3.4.5 (cuda)

Red Hat AI Inference Model Optimization Tools 3.4.5 cuda is now available. Red Hat AI Inference Model Optimization Tools...

CVE-2026-88416

MCMS 6.1.1 through 6.2.1 has a SQL injection vulnerability in the custom model/form import feature...

CVE-2026-77255

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to 0.22.0, the Jira updateissue attachments argument is converted into local paths and routed to the attachment upload implementation without workspace validation. A caller can make the MCP serv...