Sign in
Deutsch English Español Polski
Low

langchain Server-Side Request Forgery vulnerability

  • Disclosed: 26.02.2024
  • Updated: 11.10.2026 13:18

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

Affected software

Click a technology to see all vulnerabilities affecting it.

PlatformPackageVulnerable versionsFixed in
Python (PyPI) langchain < 0.1.0 0.1.0
Python (PyPI) langchain-exa < 0.1.0 0.1.0

References

CVSS score 3.7/10
CVSS vector
CVSS:3.0/AV:L/AC:H/PR:H/UI:R/S:C/C:L/I:L/A:N
Weakness (CWE)
CWE-918
Platform
Python (PyPI)
Package
langchain, langchain-exa
Disclosed
26.02.2024
Updated
11.10.2026 13:18

Sources and licenses

OSV / GitHub Advisory Database - PYSEC-2024-235 - PyPA Advisory Database; CC BY 4.0

OSV / GitHub Advisory Database - GHSA-h9j7-5xvc-qhg5 - CC BY 4.0

OSV / GitHub Advisory Database - PYSEC-2026-1509 - PyPA Advisory Database; CC BY 4.0

Vulnerability history: langchain

All published vulnerabilities of this package (Python (PyPI)), newest first. Shows whether this is a one-off slip or a package that needs watching.

All (22) in the archive
Total entries
22
First → latest
04.2023 06.2026
Without a fix
0
Exploited in attacks
0

Severity breakdown

  • Critical 12
  • High 4
  • Medium 4
  • Low 2

Disclosures per year

Severity:
  1. LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning
    High · 7.1 CVE-2026-45134 < 0.3.30 0.3.30
  2. langchain Server-Side Request Forgery vulnerability this entry
    Low · 3.7 CVE-2024-0243 < 0.1.0 0.1.0
  3. Langchain Server-Side Request Forgery vulnerability
    High · 7.5 CVE-2023-32786 < 0.0.329 0.0.329
  4. Langchain SQL Injection vulnerability
    Critical · 9.8 CVE-2023-32785 < 0.0.247 0.0.247
  5. 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.
    High · 8.8 CVE-2023-46229 < 0.0.317 0.0.317
  6. 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.
    Critical · 9.8 CVE-2023-39631 < 0.0.308 0.0.308
  7. An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via the via the a json file to the load_prompt parameter.
    Critical · 9.8 CVE-2023-36281 < 0.0.171 0.0.171
  8. 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.
    Critical · 9.8 CVE-2023-38896 < 0.0.195 0.0.195
  9. 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.
    Critical · 9.8 CVE-2023-39659 < 0.0.233 0.0.233
  10. An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.
    Critical · 9.8 CVE-2023-38860 < 0.0.247 0.0.247
  11. 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_obje
    Critical · 9.8 CVE-2023-36095 < 0.0.236 0.0.236
  12. SQL injection vulnerability in langchain v.0.0.64 allows a remote attacker to obtain sensitive information via the SQLDatabaseChain component.
    High · 7.5 CVE-2023-36189 < 0.0.247 0.0.247
  13. langchain vulnerable to arbitrary code execution
    Critical · 9.8 CVE-2023-36188 < 0.0.247 0.0.247
  14. An issue in langchain v.0.0.199 allows an attacker to execute arbitrary code via the PALChain in the python exec method.
    Critical · 9.8 CVE-2023-36258 < 0.0.247 0.0.247
  15. Langchain 0.0.171 is vulnerable to Arbitrary code execution in load_prompt.
    Critical · 9.8 CVE-2023-34541 < 0.0.247 0.0.247
  16. Langchain 0.0.171 is vulnerable to Arbitrary Code Execution.
    Critical · 9.8 CVE-2023-34540 < 0.0.225 0.0.225
  17. In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
    Critical · 9.8 CVE-2023-29374 < 0.0.132 0.0.132

Know which vulnerabilities affect your application

With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.

Connect your application
DockRay newsletter

Application security in your inbox

Important vulnerabilities, actionable guidance and practical advice for your applications. Choose your technologies and follow what matters to your project.

  • A daily digest of new vulnerabilities, critical ones included.
  • Notifications about important updates.
  • Practical advice on application security and monitoring.

Leave empty to receive updates for every technology.

Privacy policy

Free to subscribe. Unsubscribe with one click in any email.