CVE-2026-41488

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 v3 3.1 LOW

3.1^/10

CVSS v3 : LOW

Vector :

Exploitability : 1.6 / Impact : 1.4

Attack Vector NETWORK

Attack Complexity HIGH

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact LOW

Integrity Impact NONE

Availability Impact NONE

Scope UNCHANGED

References

Link	Resource
https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r	Mitigation Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:langchain:langchain-openai:*:*:*:*:*:*:*:*

History

26 Oct 2026, 21:10

Type	Values Removed	Values Added
Summary		(es) LangChain es un framework para construir agentes y aplicaciones impulsadas por LLM. Antes de la versión 1.1.14, el asistente _url_to_size() de langchain-openai (utilizado por get_num_tokens_from_messages para el recuento de tokens de imagen) validaba las URL para la protección contra SSRF y luego las obtenía en una operación de red separada con resolución DNS independiente. Esto dejaba una ventana de TOCTOU / revinculación de DNS: un nombre de host controlado por un atacante podría resolverse a una IP pública durante la validación y luego a una IP privada/localhost durante la obtención real.

Information

Published : 2026-04-24 21:16

Updated : 2026-10-26 21:10

NVD link : CVE-2026-41488

Mitre link : CVE-2026-41488

CVE.ORG link : CVE-2026-41488

JSON object : View

Products Affected

langchain

langchain-openai

CWE

CWE-918

Server-Side Request Forgery (SSRF)

{"id": "CVE-2026-41488", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-41488", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-04-27T13:40:34.758273Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 3.1, "attackVector": "NETWORK", "baseSeverity": "LOW", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "REQUIRED", "attackComplexity": "HIGH", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "LOW"}, "impactScore": 1.4, "exploitabilityScore": 1.6}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "langchain-ai", "product": "langchain-openai", "versions": [{"status": "affected", "version": "< 1.1.14"}]}]}], "published": "2026-04-24T21:16:19.637", "references": [{"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r", "tags": ["Mitigation", "Vendor Advisory"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-918"}]}], "descriptions": [{"lang": "en", "value": "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."}, {"lang": "es", "value": "LangChain es un framework para construir agentes y aplicaciones impulsadas por LLM. Antes de la versi\u00f3n 1.1.14, el asistente _url_to_size() de langchain-openai (utilizado por get_num_tokens_from_messages para el recuento de tokens de imagen) validaba las URL para la protecci\u00f3n contra SSRF y luego las obten\u00eda en una operaci\u00f3n de red separada con resoluci\u00f3n DNS independiente. Esto dejaba una ventana de TOCTOU / revinculaci\u00f3n de DNS: un nombre de host controlado por un atacante podr\u00eda resolverse a una IP p\u00fablica durante la validaci\u00f3n y luego a una IP privada/localhost durante la obtenci\u00f3n real."}], "lastModified": "2026-10-26T21:10:00.170", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:langchain:langchain-openai:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "8089EE72-7257-4263-BF4E-8B429B2C0002", "versionEndExcluding": "1.1.14"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}