CVE-2026-41488

< 1.1.14

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's _url_to_size() help

3.1LOW

CVE-2026-41481

< 1.1.2

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTex

6.5MEDIUM

CVE-2026-40087

< 0.3.84

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangChain's f-string prompt

5.3MEDIUM

CVE-2026-34070

< 1.2.22

LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchai

7.5HIGH

CVE-2026-27795

< 1.1.18

LangChain is a framework for building LLM-powered applications. Prior to version 1.1.8, a redirect-based Server-Side Request Forge

4.1MEDIUM

CVE-2026-26019

< 1.1.14

LangChain is a framework for building LLM-powered applications. Prior to 1.1.14, the RecursiveUrlLoader class in @langchain/commun

4.1MEDIUM

CVE-2026-26013

< 1.2.11

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_mes

3.7LOW

CVE-2024-58340

<= 0.3.1

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service (ReDoS) vulnerability in the MRKLOutpu

7.5HIGH

CVE-2025-68665

< 0.3.37

LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to l

8.6HIGH

CVE-2025-68664

< 0.3.81

LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization inj

9.3CRITICAL

CVE-2025-2828

< 0.0.28

A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (spe

10.0CRITICAL

CVE-2024-8309

all versions

A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt in

9.8CRITICAL

CVE-2024-7774

all versions

A path traversal vulnerability exists in the getFullPath method of langchain-ai/langchainjs version 0.2.5. This vulnerability al

9.1CRITICAL

CVE-2024-7042

< 0.3.1

A vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows

9.8CRITICAL

CVE-2024-46946

>= 0.1.17 and <= 0.3.0

langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code

9.8CRITICAL

CVE-2024-5998

< 0.2.9

A vulnerability in the FAISS.deserialize_from_bytes function of langchain-ai/langchain allows for pickle deserialization of untrus

7.8HIGH

CVE-2024-21513

>= 0.0.15 and < 0.0.21

Versions of the package langchain-experimental from 0.0.15 and before 0.0.21 are vulnerable to Arbitrary Code Execution when retri

8.5HIGH

CVE-2024-38459

< 0.0.61

langchain_experimental (aka LangChain Experimental) before 0.0.61 for LangChain provides Python REPL access without an opt-in step

7.8HIGH

CVE-2024-3095

>= 0.1.5 and < 0.2.9

A Server-Side Request Forgery (SSRF) vulnerability exists in the Web Research Retriever component of langchain-ai/langchain versio

7.7HIGH

CVE-2024-2965

< 0.2.5

A Denial-of-Service (DoS) vulnerability exists in the SitemapLoader class of the langchain-ai/langchain repository, affecting

4.7MEDIUM

CVE-2024-3571

all versions

langchain-ai/langchain is vulnerable to path traversal due to improper limitation of a pathname to a restricted directory ('Path T

8.8HIGH

CVE-2024-1455

>= 0.1.4 and <= 0.1.35

A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) e

5.9MEDIUM

CVE-2024-28088

< 0.1.12

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in

8.1HIGH

CVE-2024-2057

all versions

A vulnerability was found in LangChain langchain_community 0.0.26. It has been classified as critical. Affected is the function lo

6.3MEDIUM

CVE-2024-27444

< 0.1.8

langchain_experimental (aka LangChain Experimental) in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix

9.8CRITICAL

CVE-2024-0243

< 0.1.0

With the following crawler configuration: ```python from bs4 import BeautifulSoup as Soup url = "https://example.com" loader = R

8.1HIGH

CVE-2023-32786

<= 0.0.155

In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, ess

7.5HIGH

CVE-2023-46229

< 0.0.317

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

8.8HIGH

CVE-2023-39631

all versions

An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary code via the evaluate function in the nu

9.8CRITICAL

CVE-2023-36281

all versions

An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt. This is related

9.8CRITICAL

CVE-2023-39659

<= 0.0.232

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

9.8CRITICAL

CVE-2023-38896

<= 0.0.194

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

9.8CRITICAL

CVE-2023-38860

all versions

An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.

9.8CRITICAL

CVE-2023-36095

all versions

An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALCh

9.8CRITICAL

CVE-2023-36189

all versions

SQL injection vulnerability in langchain before v0.0.247 allows a remote attacker to obtain sensitive information via the SQLDatab

7.5HIGH

CVE-2023-36188

all versions

An issue in langchain v.0.0.64 allows a remote attacker to execute arbitrary code via the PALChain parameter in the Python exec me

9.8CRITICAL

CVE-2023-36258

all versions

An issue in LangChain before 0.0.236 allows an attacker to execute arbitrary code because Python code with os.system, exec, or eva

9.8CRITICAL

CVE-2023-34541

all versions

Langchain 0.0.171 is vulnerable to Arbitrary code execution in load_prompt.

9.8CRITICAL

CVE-2023-34540

all versions

Langchain before v0.0.225 was discovered to contain a remote code execution (RCE) vulnerability in the component JiraAPIWrapper (a

9.8CRITICAL

CVE-2023-29374

<= 0.0.131

In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Pytho

9.8CRITICAL