CVE-2024-27444

langchainexperimental aka LangChain Experimental in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the import, subclasses, builtins, globals, getattribute, bases, mro, or base attribute in Python code. These are not prohibited by...

Authentication flaw

langchainexperimental aka LangChain Experimental in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the import, subclasses, builtins, globals, getattribute, bases, mro, or base attribute in Python code. These are not prohibited by...

genai-agents (>=0.1.0 <=0.1.3), openagi (>=0.1.0b0 <=0.1.0b4) potentially affected by CVE-2024-0243 via langchain-exa (=0.0.1)

langchain-exa PYPI version =0.0.1 is affected by a known vulnerability. The following packages have a transitive dependency on langchain-exa and may be impacted: - genai-agents =0.1.0, =0.1.0b0, =0.1.0b4 Source cves: CVE-2024-0243 Source advisory: OSV:PYSEC-2024-235...

CVE-2024-0243

With the following crawler configuration: python from bs4 import BeautifulSoup as Soup url = "https://example.com" loader = RecursiveUrlLoader url=url, maxdepth=2, extractor=lambda x: Soupx, "html.parser".text docs = loader.load An attacker in control of the contents of https://example.com could...

LangChain Code Issues Vulnerabilities

LangChain is building applications using LLM through composability. LangChain is vulnerable to a code issue. An attacker could use this vulnerability to place a malicious HTML file with a link such as "https://example.completely.different/myfile.html" in it, allowing the crawler to continue...

LangChain Security Breach

LangChain is used to build applications using LLM through composability. A security vulnerability exists in LangChain versions prior to 0.1.8 that stems from a vulnerability that allows an attacker to bypass and execute arbitrary code via properties in Python code...

CVE-2024-27444

langchainexperimental aka LangChain Experimental in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the import, subclasses, builtins, globals, getattribute, bases, mro, or base attribute in Python code. These are not prohibited by...

CVE-2024-27444

The CVE-2024-27444 entry applies to langchain_experimental (LangChain Experimental) in LangChain prior to 0.1.8, where an attacker can bypass the fixes for CVE-2023-44467 and execute arbitrary Python code via privileged attributes (import , subclasses , builtins , globals , getattribute , bases ,...

CVE-2024-27444

langchainexperimental aka LangChain Experimental in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the import, subclasses, builtins, globals, getattribute, bases, mro, or base attribute in Python code. These are not prohibited by...

PT-2024-21902

Name of the Vulnerable Software and Affected Versions LangChain versions prior to 0.1.8 langchain experimental versions prior to 0.0.52 Description The issue allows an attacker to bypass a previous fix and execute arbitrary code via certain attributes in Python code, including import , subclasses...

CVE-2024-0243 Server-side Request Forgery In Recursive URL Loader

With the following crawler configuration: python from bs4 import BeautifulSoup as Soup url = "https://example.com" loader = RecursiveUrlLoader url=url, maxdepth=2, extractor=lambda x: Soupx, "html.parser".text docs = loader.load An attacker in control of the contents of https://example.com could...

PT-2024-15407

Name of the Vulnerable Software and Affected Versions langchain versions prior to the version that includes the fix from https://github.com/langchain-ai/langchain/pull/15559 Description The issue arises when an attacker controls the contents of a website, such as https://example.com, and places a...

couchbase-mcp-server (>=0.3.1rc2 <=0.5.0), couchbase-sqlalchemy (=1.0.3) +4 more potentially affected by CVE-2023-45875 via couchbase (>=4.1.8 <=4.5.0)

couchbase PYPI version =4.1.8, =0.3.1rc2, =0.2.2.dev0, =1.0.2 - pyxi-azdo-analytics =0.0.1 - pyxi-couchbase-client =0.0.10 Source cves: CVE-2023-45875 Source advisory: OSV:PYSEC-2023-235...

Server Side Request Forgery (SSRF)

langchain is vulnerable to Server Side Request Forgery SSRF. The attacker can force the service to retrieve an arbitrary url which could lead to information leak. Also can potentially inject content into downstream tasks...

SQL Injection

langchain is vulnerable to SQL Injection. The vulnerability is due to a prompt injection which allows execution of arbitrary code against the SQL service provided by the chain...

agent-actors (=0.1.0), agent-reader (>=0.2.1 <=0.2.2) +176 more potentially affected by CVE-2023-32785 via langchain (>=0.0.100 <=0.0.246)

langchain PYPI version =0.0.100, =0.2.1, =0.1.0, =0.1.5, =0.0.1, =0.0.1, =0.0.1, =0.0.5, =0.0.14, =0.1.9, =0.0.33, =0.1.0a0, =0.2.0, =0.1.3, =0.1.5 and more Source cves: CVE-2023-32785 Source advisory: OSV:GHSA-8H5W-F6Q9-WG35...

GHSA-8H5W-F6Q9-WG35 Langchain SQL Injection vulnerability

In Langchain before 0.0.247, prompt injection allows execution of arbitrary code against the SQL service provided by the chain...

agent-actors (=0.1.0), agent-lab-sdk (>=0.1.7 <=0.1.16) +286 more potentially affected by CVE-2023-32786 via langchain (>=0.0.100 <=0.0.327)

langchain PYPI version =0.0.100, =0.1.7, =0.2.1, =0.1.0, =0.1.5, =0.0.2, =0.0.1, =0.0.1, =0.0.1, =0.0.1, =0.1.8, =0.0.5, =0.0.14, =0.0.18 - athina =0.1.0 and more Source cves: CVE-2023-32786 Source advisory: OSV:GHSA-6H8P-4HX9-W66C...

GHSA-6H8P-4HX9-W66C Langchain Server-Side Request Forgery vulnerability

In Langchain before 0.0.329, 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...

Langchain Server-Side Request Forgery vulnerability

In Langchain before 0.0.329, 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...