Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks

Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and GraphChain. Nevertheless, this agentic environment increases the probability of the occurrence of multimodal prompt

injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper

stored cross-site scripting (XSS) vulnerability in @n8n/n8n-nodes-langchain.chatTrigger. An authorized user can configure the LangChain Chat Trigger node with malicious JavaScript in the initialMessages field and enable public access

langchain-ai/langchain project, specifically the EverNoteLoader component, is vulnerable to XML External Entity (XXE) attacks due to insecure XML parsing. The affected version is 0.3.63. The vulnerability arises from

Insecure permissions in LangChain-ChatGLM-Webui commit ef829 allows attackers to arbitrarily view and download sensitive files via supplying a crafted request

vulnerability, which was classified as critical, has been found in chatchat-space Langchain-Chatchat up to 0.3.1. This issue affects some unknown processing of the file /v1/file. The manipulation

vulnerability classified as problematic was found in chatchat-space Langchain-Chatchat up to 0.3.1. This vulnerability affects unknown code of the file /v1/files?purpose=assistants. The manipulation leads to path

vulnerability classified as critical has been found in chatchat-space Langchain-Chatchat up to 0.3.1. This affects the function upload_temp_docs of the file /knowledge_base/upload_temp_docs of the component Backend

vulnerability in langchain-core versions >=0.1.17,<0.1.53, >=0.2.0,<0.2.43, and >=0.3.0,<0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability

vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial

path traversal vulnerability exists in the `getFullPath` method of langchain-ai/langchainjs version 0.2.5. This vulnerability allows attackers to save files anywhere in the filesystem, overwrite existing text files, read

vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits unauthorized data

vulnerability in the FAISS.deserialize_from_bytes function of langchain-ai/langchain allows for pickle deserialization of untrusted data. This can lead to the execution of arbitrary commands via the os.system

Denial of service in langchain-community

Server-Side Request Forgery (SSRF) vulnerability exists in the Web Research Retriever component of langchain-ai/langchain version 0.1.5. The vulnerability arises because the Web Research Retriever does not restrict

versions of the MLflow platform running version 2.5.0 or newer, enabling a maliciously uploaded Langchain AgentExecutor model to run arbitrary code on an end user’s system when interacted with

langchain-ai/langchain is vulnerable to path traversal due to improper limitation of a pathname to a restricted directory ('Path Traversal') in its LocalFileStore functionality. An attacker can leverage this

vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within

Langchain SQL Injection vulnerability

Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks