llm-security

New: Demonstrating Indirect Injection attacks on Bing Chat Compromising LLMs using Indirect Prompt Injection "... a language model is a Turing-complete weird machine running programs written in natural language; when you do retrieval, you are not 'plugging updated facts into your AI', you are...

CVE-2024-8309

Prueba de Concepto para la Vulnerabilidad CVE-2024–8309 de Langchain Descripción general Esta configuración demuestra una prueba de concepto de la vulnerabilidad de inyección de prompts en la clase GraphCypherQAChain que permite la inyección de SQL en una base de datos Neo4j. Componentes: 1. Base...

LangAlpha

The harness for agentic trading. Open-source AI agents that research the market, build the thesis, and trade your own brokerage account within the permissions you set. Try LangAlpha ↗ · Get started · Agentic trading · Harness design · Full-stack architecture · Security English · 简体中文 · 日本語 Why...

Nmap-API

API de Nmap Usa python3.10, Debian, python-Nmap y el framework flask para crear una API de Nmap que puede realizar escaneos con buena velocidad en línea y es fácil de desplegar. Esta es una implementación para nuestro proyecto universitario PCL que aún está en desarrollo y se actualiza...

EUVD-2026-93771

LangChain: MongoDBChatMessageHistory query injection can allow cross-session access...

CVE-2026-34070

I Found a Path Traversal Bug in LangChain That Could Leak Your Cloud Credentials How a forgotten legacy API in one of AI's most popular frameworks quietly exposed millions of applications to arbitrary file reads. There's a certain feeling you get when a proof-of-concept works on the first try. No...

CVE-2025-68664

CVE-2025-68664 Todo lo que quiero para Navidad son tus secretos: LangGrinch golpea el núcleo de LangChain CVE-2025-68664 Autor: Yarden Porat Investigación de Cyata: Vulnerabilidad LangGrinch en LangChain Publicado: https://cyata.ai/blog/langgrinch-langchain-core-cve-2025-68664/ Ayer, LangChain...

CVE-2024-21513

CVE-2024-21513 PoC para CVE-2024-21513 Exploit original documentado por Snyk Security Research Exploit CVE-2024-21513 es una vulnerabilidad en langchain-experimental donde los resultados no validados de consultas SQL se pasaban a eval de Python, permitiendo la ejecución remota de código mediante...

CVE-2026-106119

LangChain is a framework for building LLM-powered applications. Prior to 1.3.1, MongoDBChatMessageHistory does not enforce the documented string type for an untrusted structured session identifier at runtime, allowing the identifier to be interpreted as a MongoDB query condition rather than as a...

CVE-2026-106119 LangChain: MongoDBChatMessageHistory query injection can allow cross-session access

LangChain is a framework for building LLM-powered applications. Prior to 1.3.1, MongoDBChatMessageHistory does not enforce the documented string type for an untrusted structured session identifier at runtime, allowing the identifier to be interpreted as a MongoDB query condition rather than as a...

CVE-2026-106119

The LangChain framework is vulnerable to a query injection flaw in the MongoDBChatMessageHistory component prior to version 1.3.1 . The root cause is a failure to enforce the documented string type for untrusted structured session identifiers at runtime, which allows these identifiers to be inter...

CVE-2026-106119 LangChain: MongoDBChatMessageHistory query injection can allow cross-session access

LangChain is a framework for building LLM-powered applications. Prior to 1.3.1, MongoDBChatMessageHistory does not enforce the documented string type for an untrusted structured session identifier at runtime, allowing the identifier to be interpreted as a MongoDB query condition rather than as a...

CVE-2026-106119 LangChain: MongoDBChatMessageHistory query injection can allow cross-session access

LangChain is a framework for building LLM-powered applications. Prior to 1.3.1, MongoDBChatMessageHistory does not enforce the documented string type for an untrusted structured session identifier at runtime, allowing the identifier to be interpreted as a MongoDB query condition rather than as a...

LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values

Summary @langchain/redis did not properly escape values used to construct structured RediSearch TAG and TEXT filters. An application that passes attacker-controlled values into these filters could allow the attacker to alter the resulting search query. Affected versions @langchain/redis versions...

GHSA-5X6V-P487-7QH2 LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values

Summary @langchain/redis did not properly escape values used to construct structured RediSearch TAG and TEXT filters. An application that passes attacker-controlled values into these filters could allow the attacker to alter the resulting search query. Affected versions @langchain/redis versions...

CVE-2026-105799

LangChain is a framework for building LLM-powered applications. Prior to 1.1.1, @langchain/redis does not escape attacker-controlled values in structured RediSearch TAG filters and structured RediSearch TEXT filters, allowing injected RediSearch syntax to alter or broaden the generated search...

CVE-2026-105799

The @langchain/redis component in LangChain (prior to version 1.1.1 ) is vulnerable to RediSearch Filter Injection due to a failure to escape attacker-controlled values in structured TAG and TEXT filters. An attacker can inject RediSearch syntax to modify or broaden search queries. If an applicat...

EUVD-2026-93431

LangChain is a framework for building LLM-powered applications. Prior to 1.1.1, @langchain/redis does not escape attacker-controlled values in structured RediSearch TAG filters and structured RediSearch TEXT filters, allowing injected RediSearch syntax to alter or broaden the generated search...

CVE-2026-105799 LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values

LangChain is a framework for building LLM-powered applications. Prior to 1.1.1, @langchain/redis does not escape attacker-controlled values in structured RediSearch TAG filters and structured RediSearch TEXT filters, allowing injected RediSearch syntax to alter or broaden the generated search...

CVE-2026-105799 LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values

LangChain is a framework for building LLM-powered applications. Prior to 1.1.1, @langchain/redis does not escape attacker-controlled values in structured RediSearch TAG filters and structured RediSearch TEXT filters, allowing injected RediSearch syntax to alter or broaden the generated search...