Langchain

LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.

Published: 2026-03-31T02:01:49.320Z
Updated: 2026-03-31T18:04:59.283Z

A 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 manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in multi-tenant security environments, and data integrity issues. Attackers can create, update, or delete nodes and relationships without proper authorization, extract sensitive data, disrupt services, access data across different tenants, and compromise the integrity of the database.

Published: 2024-10-29T12:50:05.375Z
Updated: 2025-10-15T12:50:36.199Z

A 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 function. The issue affects the latest version of the product.

Published: 2024-09-17T11:50:13.813Z
Updated: 2024-09-17T13:34:15.648Z

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service (ReDoS) vulnerability in the MRKLOutputParser.parse() method (libs/langchain/langchain/agents/mrkl/output_parser.py). The parser applies a backtracking-prone regular expression when extracting tool actions from model output. An attacker who can supply or influence the parsed text (for example via prompt injection in downstream applications that pass LLM output directly into MRKLOutputParser.parse()) can trigger excessive CPU consumption by providing a crafted payload, causing significant parsing delays and a denial-of-service condition.

Published: 2026-01-12T23:05:00.801Z
Updated: 2026-03-05T01:29:48.307Z

A 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 requests to remote internet addresses, allowing it to reach local addresses. This flaw enables attackers to execute port scans, access local services, and in some scenarios, read instance metadata from cloud environments. The vulnerability is particularly concerning as it can be exploited to abuse the Web Explorer server as a proxy for web attacks on third parties and interact with servers in the local network, including reading their response data. This could potentially lead to arbitrary code execution, depending on the nature of the local services. The vulnerability is limited to GET requests, as POST requests are not possible, but the impact on confidentiality, integrity, and availability is significant due to the potential for stolen credentials and state-changing interactions with internal APIs.

Published: 2024-06-06T18:28:56.403Z
Updated: 2024-08-01T19:32:42.601Z

A Denial-of-Service (DoS) vulnerability exists in the `SitemapLoader` class of the `langchain-ai/langchain` repository, affecting all versions. The `parse_sitemap` method, responsible for parsing sitemaps and extracting URLs, lacks a mechanism to prevent infinite recursion when a sitemap URL refers to the current sitemap itself. This oversight allows for the possibility of an infinite loop, leading to a crash by exceeding the maximum recursion depth in Python. This vulnerability can be exploited to occupy server socket/port resources and crash the Python process, impacting the availability of services relying on this functionality.

Published: 2024-06-06T18:52:54.353Z
Updated: 2025-10-15T12:50:22.559Z

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)

Published: 2024-03-03T00:00:00.000Z
Updated: 2024-08-26T19:44:45.330Z

A 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 an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading to a denial of service (DoS).

Published: 2024-03-26T14:03:46.647Z
Updated: 2024-08-15T15:56:19.154Z

With the following crawler configuration: ```python from bs4 import BeautifulSoup as Soup url = "https://example.com" loader = RecursiveUrlLoader( url=url, max_depth=2, extractor=lambda x: Soup(x, "html.parser").text ) docs = loader.load() ``` An attacker in control of the contents of `https://example.com` could place a malicious HTML file in there with links like "https://example.completely.different/my_file.html" and the crawler would proceed to download that file as well even though `prevent_outside=True`. https://github.com/langchain-ai/langchain/blob/bf0b3cc0b5ade1fb95a5b1b6fa260e99064c2e22/libs/community/langchain_community/document_loaders/recursive_url_loader.py#L51-L51 Resolved in https://github.com/langchain-ai/langchain/pull/15559

Published: 2024-02-24T17:59:26.498Z
Updated: 2025-04-22T16:14:26.674Z

LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an internal server.

Published: 2023-10-19T00:00:00.000Z
Updated: 2024-09-12T18:06:21.757Z

An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool._run component.

Published: 2023-08-15T00:00:00.000Z
Updated: 2024-10-08T20:28:08.726Z

An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the from_math_prompt and from_colored_object_prompt functions.

Published: 2023-08-15T00:00:00.000Z
Updated: 2024-10-09T13:02:11.603Z

In 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.

Published: 2023-10-20T00:00:00.000Z
Updated: 2024-09-12T17:54:54.643Z

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

Published: 2023-04-05T00:00:00.000Z
Updated: 2025-02-12T16:24:39.291Z