CVE-2026-26013Disclosure(langchain / langchain_core)

LOWCVSS 3.7 · LOW

Signal is active with 1 mentions in latest observed window

Immediate actions

Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

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.

langchain CVEs Back to dashboard

0.0/ 10 priority

Sources & remediation

Patch / fix

https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565

Vendor / third-party advisories

https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r

Other references

https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11

Weakness type (CWE)

CWE-918

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

AVAILABLE

Momentum

STABLE

Are you affected?

If you run products in this scope, you should treat this CVE as relevant to your environment.

langchain_core

Threat summary

4 mentions across 3 observed days
Momentum state: stable

What's happening

Technical details provided in 3 signals
Disclosure: 3 classified signals
General: 1 classified signal
Peaked 1d ago at 2 mentions (2026-02-11); latest day: 1
4 total mentions across 3 days

Affected systems

Vendors

langchain

Products

langchain_core

Deep dive

Activity timeline4 mentions / 3d

Signal classification2 categories

Disclosure

375.0%

General

125.0%

Referenced assets3 URLs

By indicator

Classification over time

Date	Total	Labels

2026-02-10	1	General1
2026-02-11	2	Disclosure2
2026-02-16	1	Disclosure1

Full discourse4 posts

CVE@CVEnew240d
General
CVE-2026-26013 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 ima… https://www.cve.org/CVERecord?id=CVE-2026-26013
Post summary
The post simply notes the existence of CVE-2026-26013 related to LangChain, but provides no PoC, exploit, active use, patch, or detailed technical information.
00020217
56.5K followersView on X
RagingCISO@CisoRaging77913235d
Disclosure
CVE-2026-26013: LangChain fetches any URL in image prompts—no validation. Token counting function becomes SSRF tunnel to your cloud metadata. "AI-native" framework in prod without network review? Your LLM now proxies for attackers. But hey, it counts tokens real good.
Post summary
The post discloses a new LangChain vulnerability (CVE-2026-26013) that allows arbitrary URL fetching in image prompts, creating an SSRF tunnel to cloud metadata via the token counting function.
1000038
3 followersView on X
Vulmon Vulnerability Feed@VulmonFeeds240d
Disclosure
CVE-2026-26013 Server-Side Request Forgery in LangChain ChatOpenAI Before Version 1.2.11 https://vulmon.com/vulnerabilitydetails?qid=CVE-2026-26013
Post summary
A new server‑side request forgery vulnerability (CVE‑2026‑26013) has been identified in LangChain ChatOpenAI versions before 1.2.11.
00010109
4.0K followersView on X
cvereports@_cvereports239d
Disclosure
CVE-2026-26013: CVE-2026-26013: When Your AI Assistant Browses Your Intranet In the race to build the ultimate AI agent, developers often overlook the plumbing. CVE-2026-26013 is a classic Server-Side Request Forgery (SSRF) vulnerability nestled deep ... https://cvereports.com/reports/CVE-2026-26013
Post summary
CVE-2026-26013 is announced as a Server‑Side Request Forgery vulnerability affecting AI assistant intranet browsing, but the post lacks exploitation details, patch information, or evidence of active attacks.
0000037
27 followersView on X

CPE platform detail1 entries

Part:

Vendor:

Product:

Version:

Target SW:

Target HW:

1 of 1 entries

Part	Vendor	Product	Version	Target SW	Target HW
App	langchain	langchain_core	-	python	-

Explore more

Back to dashboard langchain CVEs langchain_core vulnerabilities

What researchers are saying

CVE-2026-26013

CVE@CVEnewGeneral

The post simply notes the existence of CVE-2026-26013 related to LangChain, but provides no PoC, exploit, active use, patch, or detailed technical information.

RagingCISO@CisoRaging77913Disclosure

The post discloses a new LangChain vulnerability (CVE-2026-26013) that allows arbitrary URL fetching in image prompts, creating an SSRF tunnel to cloud metadata via the token counting function.

Vulmon Vulnerability Feed@VulmonFeedsDisclosure

A new server‑side request forgery vulnerability (CVE‑2026‑26013) has been identified in LangChain ChatOpenAI versions before 1.2.11.

cvereports@_cvereportsDisclosure

CVE-2026-26013 is announced as a Server‑Side Request Forgery vulnerability affecting AI assistant intranet browsing, but the post lacks exploitation details, patch information, or evidence of active attacks.