CVE-2023-32786 Langchain Server-Side Request Forgery vulnerability
Attackers can exploit prompt injection in Langchain to trigger Server-Side Request Forgery, accessing arbitrary URLs and potentially injecting malicious content.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2023-32786?
CVE-2023-32786 is a high-severity server-side request forgery vulnerability in n/a, published on 20 Oct 2023. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Weakness: CWE-74
Which versions are affected by CVE-2023-32786?
3 open source packages ship an affected version, including langchain. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
langchain PyPI | All versions | 0.0.329 |
langchain PyPI | All versions | 0.0.329 |
langchain PyPI | All versions | 0.0.329 |
Products include Langchain Langchain.
How do I fix CVE-2023-32786?
Upgrade langchain to 0.0.329 or later.
Upgrade, and send outbound requests through an allow-list that blocks internal addresses. More about Server-side request forgery.
Is CVE-2023-32786 being exploited?
There is no known exploitation of CVE-2023-32786 in the wild and no public exploit code.
Other vulnerabilities in n/a
- CVE-2023-39631 Langchain vulnerable to arbitrary code execution via the evaluate function in the numexpr library
- CVE-2023-36281 langchain vulnerable to arbitrary code execution
- CVE-2023-38860 LangChain vulnerable to arbitrary code execution
- CVE-2023-38896 LangChain vulnerable to arbitrary code execution
- CVE-2023-39659 LangChain vulnerable to arbitrary code execution
Sources
Also known as GHSA-6h8p-4hx9-w66c, PYSEC-2026-1508.