LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method

Flexible GraphRAG is a Python framework for building graph and

unstructured: Server-Side Request Forgery in the URL-based partitioning

Proof-of-Execution Memory: Defending LLM Agents Against Forged-Reasoning Attacks by Verifying What Actually Happened

attacks aimed at itself, adds microseconds of overhead, and works unchanged in a real LangChain agent. PoEM protects exactly the decisions it gates

Open WebUI has a SSRF Bypass via HTTP Redirect Following

LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust

Robust Agent Compensation (RAC): Teaching AI Agents to Compensate

existing agent frameworks via their existing extension points. We present an implementation based on LangChain, demonstrate its viability through the $τ$-bench and REALM-Bench, and show that when solving

LangSmith Client SDKs has Prototype Pollution in langsmith-sdk via

From Storage to Steering: Memory Control Flow Attacks on LLM Agents

Gemini 2.5 Flash on real-world tools from two major LLM agent development frameworks, LangChain and LlamaIndex. The results show that in general over 90% trials are vulnerable to MCFA

LangGraph checkpoint loading has unsafe msgpack deserialization

Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation

agent coordination. The suggested system utilizes specialized security agents coordinated with the help of LangChain and LangGraph, communicates with actual CI/CD environments with the Model Context Protocol (MCP), and documents

SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models

OWASP LLM Top 10 2025 categories across more than 40 frameworks, including LangChain, OpenAI, and Hugging Face). Every example follows a 4-turn conversational structure -- feature request; vulnerable and secure

LAPRAD: LLM-Assisted PRotocol Attack Discovery

different LLM automatically constructs the corresponding attack configurations using the ReACT approach implemented via LangChain (DNS zone file generation). Finally, in the third stage, we validate the attack's functionality