3.1

CVE-2026-41488: langchain-ai langchain-openai Server-Side Request Forgery (SSRF)

CVSS: 3.1v3.1LowAnalyzed
AliasesGHSA-r7w7-9xr2-qq2rPYSEC-2026-76
Published 24-04-2026Last modified 27-04-2026
Open JSON

Vulnerability summary

CVE-2026-41488 is a low (CVSS 3.1) Server-Side Request Forgery (SSRF) vulnerability in langchain-ai langchain-openai. EPSS estimates a 0.24% chance of exploitation in the next 30 days, higher than 14% of scored vulnerabilities.

Overall risk
12/100
0100
Low · default modelHow is this calculated?
CVSS score
3.1/10
010
Low · v3.1 (CVE.org)
EPSS score
0.24%
0%100%
Low · +0.08 pp in 30 days
KEVNot listedIn no KEV catalog
RansomwareNone recordedNo known use recorded
Public exploits0No public exploits recorded

Timeline

  1. 24-04-2026
    PublishedVulnerability first disclosed.
  2. 27-04-2026
    Last modifiedVulnerability information updated.

Description

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.

CVSS metrics

3 scores · 3 sources · 1 version

EPSS trend

Probability

0.24%

Chance of exploitation in the next 30 days

Percentile

14%

Versus all other CVEs

30-day change

+0.08 pp

From 0.16% on 20-09-2026

20-09-202620-10-2026
EPSS score
0.24%

Known exploited

Compare KEV catalogs

Not in any of the 3 tracked catalogs.

Public exploits

0 found

No public exploits indexed.

Weaknesses

CWE · root cause

Affected systems

Langchain1 product
Langchain-ai1 product
PyPI1 product
  • langchain-openai< 1.1.14

3 vendors · 3 products

References

4 links