CVE-2026-26013 | LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability is fixed in 1.2.11.

Published: 2026-02-10 Last update: 2026-03-17 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-26013 is rated Low Risk (15.8/100): CVSS Low severity, with low exploitation likelihood (EPSS 0.01%). Low composite risk—no urgent action required; patch on your normal maintenance cycle and revisit priority if CVSS or EPSS increases.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2026-26013

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-02-18 0.05% 0.01% -0.04%
2 2026-02-16 0.04% 0.05% +0.01%
3 2026-02-11 — 0.04% —

Full EPSS history (3 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-26013

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
3.7 3.1 LOW
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:H)
Even with access, the exploit needs extra luck, timing, or a fussy environment to actually work.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:N)
Doesn’t really leak secrets in a meaningful way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:L)
Might cause slowdowns, glitches, or partial disruption—not a full brick.
 2.2 1.4 [email protected]

Weakness enumeration for CVE-2026-26013

GitHub Security Advisory for CVE-2026-26013

GHSA-2g6r-c272-w58r · Severity: low · Ecosystem: pip — LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages

OS Trackers for CVE-2026-26013

vendor priority summary link
redhat low — https://access.redhat.com/security/cve/CVE-2026-26013

Affected software / configurations for CVE-2026-26013

Vendor Product Version Raw CPE
langchain langchain_core < 1.2.11 cpe:2.3:a:langchain:langchain_core:*:*:*:*:*:python:*:*

References for CVE-2026-26013

cvelogic Threat Intelligence