Langchain: >> Langchain Security Vulnerabilities
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
0.001
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
0.001
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
0.003
Published
2023-10-19
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
0.021
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
0.64
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
0.008
Published
2023-08-15
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.
CVSS Score
9.8
EPSS Score
0.012
Published
2023-08-15
An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.
CVSS Score
9.8
EPSS Score
0.014
Published
2023-08-15
An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALChain, affected functions include from_math_prompt and from_colored_object_prompt.
CVSS Score
9.8
EPSS Score
0.017
Published
2023-08-05
An issue in langchain v.0.0.64 allows a remote attacker to execute arbitrary code via the PALChain parameter in the Python exec method.
CVSS Score
9.8
EPSS Score
0.021
Published
2023-07-06