tengu

Tengu — Pentesting MCP Server "In Japanese mythology, the Tengu is a fierce mountain spirit — master strategist, warrior, and trainer of samurai. In cybersecurity, it guides you through every phase of the hunt." From recon to report — AI-assisted pentesting in one command. Tengu is an MCP server...

SecurityClaw

SecurityClaw — 自律SOCエージェントフレームワーク モジュール化されたスキルベースの自律型セキュリティ運用センター（SOC）エージェントです。OpenSearch/Elasticsearchのデータを監視し、RAGベースの行動メモリを構築し、LLMを使用してリアルタイムの異常を検証します。 Features スキルのモジュール性 — 機能を独立したフォルダとして管理。logic.py（Python）+ instruction.md（LLMガイダンス） ハートビートループ — Cron風スケジューラ：1分ごとの異常監視、6時間ごとのメモリ構築 プロバイダ非依存 —...

anticipator

Anticipator Runtime security for multi-agent AI systems. Anticipator detects prompt injection, credential leakage, encoding attacks, homoglyph spoofing, path traversal, and anomalous agent behavior across LangGraph pipelines — before they become incidents. No LLMs. No embeddings. No external APIs...

CVE-2026-104873

A flaw was found in langgraph-sdk. This vulnerability allows an authenticated attacker to bypass authorization controls to access, modify, or delete resources belonging to other users. The issue occurs because resource-scoped authorization decorators fail to restrict handlers to specified actions...

CVE-2026-104873

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From 0.1.45 until 0.4.4, the langgraph-sdk resource-scoped authorization decorators @auth.on.threads, @auth.on.assistants, and @auth.on.crons ignore the...

CVE-2026-104873

The LangGraph Python SDK is vulnerable to an authorization bypass in versions 0.1.45 through 0.4.3 . The root cause is that resource-scoped authorization decorators (@auth.on.threads , @auth.on.assistants , and @auth.on.crons ) ignore the actions argument, registering handlers for every action on...

CVE-2026-104873 LangGraph SDK custom auth silently ignores actions= on resource decorators

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From 0.1.45 until 0.4.4, the langgraph-sdk resource-scoped authorization decorators @auth.on.threads, @auth.on.assistants, and @auth.on.crons ignore the...

CVE-2026-104873 LangGraph SDK custom auth silently ignores actions= on resource decorators

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From 0.1.45 until 0.4.4, the langgraph-sdk resource-scoped authorization decorators @auth.on.threads, @auth.on.assistants, and @auth.on.crons ignore the...

CVE-langgraph

cve-id ⚡ Simple Usage Use this project only in safe and authorized environments such as: Local virtual machines Docker containers Isolated lab setups Authorized penetration testing environments Example setup: git clone cd Project use python follow below Create a virtual environment python -m venv...

CVE-2025-67644-LangGraph-3.0.1-SQLite-Checkpoint-SQL-Injection

CVE-2025-67644 PoC – LangGraph SQLite Checkpoint SQL Injection CVE-2025-67644 is a SQL Injection vulnerability CWE-89 in the langgraph-checkpoint-sqlite package part of LangGraph / LangChain ecosystem. It allows an attacker to inject arbitrary SQL via unsanitized metadata filter keys passed to th...

Security Bulletin: Multiple security vulnerabilities have been identified in Python packages shipped with IBM Guardium Cryptography Manager (GCM)

Summary Multiple security vulnerabilities identified in Python packages shipped with IBM Guardium Cryptography Manager GCM have been addressed Vulnerability Details CVEID:CVE-2026-48775 DESCRIPTION: LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB...

Security Bulletin: Multiple Vulnerabilities in IBM Concert Software

Summary Multiple vulnerabilities were addressed in IBM Concert Software version 3.0.1.1 Vulnerability Details CVEID:CVE-2026-27794 DESCRIPTION: LangGraph Checkpoint defines the base interface for LangGraph checkpointers. Prior to version 4.0.0, a Remote Code Execution vulnerability exists in...

ROOT-APP-PYPI-CVE-2026-55253 CVE-2026-55253 in langgraph-store-mongodb - Patched by Root

Root has patched CVE-2026-55253 in the langgraph-store-mongodb package for Root:PyPI. Multiple fixed versions available...

CVE-2026-55253 LangChain MongoDB: NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant data exposure

LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0, MongoDBSaver.list, MongoDBSaver.alist, and MongoDBStore.search incorporate filter dictionaries into MongoDB queries without...

EUVD-2026-77674

LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0, MongoDBSaver.list, MongoDBSaver.alist, and MongoDBStore.search incorporate filter dictionaries into MongoDB queries without...

CVE-2026-55253 LangChain MongoDB: NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant data exposure

LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0, MongoDBSaver.list, MongoDBSaver.alist, and MongoDBStore.search incorporate filter dictionaries into MongoDB queries without...

CVE-2026-55236

langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by direct reads and cro...

CVE-2026-55235

langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that transport as internal...

CVE-2026-55235

langgraph-api (the LangGraph Server runtime) prior to 0.10.0 allows a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport. The authentication middleware treats this transport as internal, so the webhook reaches the server's own thread and ru...

CVE-2026-55235 langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication

langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that transport as internal...