Langchain: Security Vulnerabilities
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.)
CVSS Score
8.1
EPSS Score
0.017
Published
2024-03-04
A vulnerability was found in LangChain langchain_community 0.0.26. It has been classified as critical. Affected is the function load_local in the library libs/community/langchain_community/retrievers/tfidf.py of the component TFIDFRetriever. The manipulation leads to server-side request forgery. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. Upgrading to version 0.0.27 is able to address this issue. It is recommended to upgrade the affected component. The identifier of this vulnerability is VDB-255372.
CVSS Score
6.3
EPSS Score
0.006
Published
2024-03-01
langchain_experimental (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 pal_chain/base.py.
CVSS Score
9.8
EPSS Score
0.008
Published
2024-02-26
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
CVSS Score
3.7
EPSS Score
0.005
Published
2024-02-26
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.
CVSS Score
7.5
EPSS Score
0.007
Published
2023-10-20
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.
CVSS Score
8.8
EPSS Score
0.447
Published
2023-10-19
langchain_experimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass the CVE-2023-36258 fix and execute arbitrary code via __import__ in Python code, which is not prohibited by pal_chain/base.py.
CVSS Score
9.8
EPSS Score
0.01
Published
2023-10-09
An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary code via the evaluate function in the numexpr library.
CVSS Score
9.8
EPSS Score
0.016
Published
2023-09-01
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 to __subclasses__ or a template.
CVSS Score
9.8
EPSS Score
0.034
Published
2023-08-22
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.
CVSS Score
9.8
EPSS Score
0.018
Published
2023-08-15