PYSEC-2026-76

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's urltosize helper used by getnumtokensfrommessages for image token counting validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS...

PYSEC-2026-77

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.splittextfromurl validated the initial URL using validatesafeurl but then performed the fetch with requests.get with redirects enabled the default. Because...

PYSEC-2026-76

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's urltosize helper used by getnumtokensfrommessages for image token counting validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS...

PYSEC-2026-77

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.splittextfromurl validated the initial URL using validatesafeurl but then performed the fetch with requests.get with redirects enabled the default. Because...

CVE-2026-41481

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.splittextfromurl validated the initial URL using validatesafeurl but then performed the fetch with requests.get with redirects enabled the default. Because...

CVE-2026-41488

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's urltosize helper used by getnumtokensfrommessages for image token counting validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS...

CVE-2026-41488 angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's urltosize helper used by getnumtokensfrommessages for image token counting validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS...

EUVD-2026-25635

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's urltosize helper used by getnumtokensfrommessages for image token counting validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS...

CVE-2026-41488 angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's urltosize helper used by getnumtokensfrommessages for image token counting validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS...

CVE-2026-41488

CVE-2026-41488 affects the langchain-openai component prior to version 1.1.14. The issue stems from the _url_to_size() helper (used by get_num_tokens_from_messages for image token counting): it validates URLs to provide SSRF protection, then fetches them in a separate network operation with an in...

CVE-2026-41481

CVE-2026-41481 affects LangChain’s HTMLHeaderTextSplitter.split_text_from_url() prior to 1.1.2. The code validates the initial URL with validate_safe_url(), but then fetches with requests.get() (redirects enabled by default) and does not revalidate redirects, allowing a URL to attacker-controlled...

CVE-2026-41481 LangChain: HTMLHeaderTextSplitter.split_text_from_url SSRF Redirect Bypass

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.splittextfromurl validated the initial URL using validatesafeurl but then performed the fetch with requests.get with redirects enabled the default. Because...

CVE-2026-41481 LangChain: HTMLHeaderTextSplitter.split_text_from_url SSRF Redirect Bypass

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.splittextfromurl validated the initial URL using validatesafeurl but then performed the fetch with requests.get with redirects enabled the default. Because...

EUVD-2026-25634

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.splittextfromurl validated the initial URL using validatesafeurl but then performed the fetch with requests.get with redirects enabled the default. Because...

CVE-2026-41481

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.splittextfromurl validated the initial URL using validatesafeurl but then performed the fetch with requests.get with redirects enabled the default. Because...

LangChain 代码问题漏洞

LangChain is an open-source framework developed by LangChain for creating applications powered by large language models LLMs. Versions of LangChain prior to 1.1.14 contained code vulnerabilities. These vulnerabilities stemmed from the urltosize helper function in langchain-openai, which, after...

langchain-text-splitters 代码问题漏洞

langchain-text-splitters is a Python package open-sourced by LangChain. Versions of langchain-text-splitters prior to 1.1.2 had code vulnerabilities. These vulnerabilities stemmed from the use of the splittextfromurl method in HTMLHeaderTextSplitter, which initiated a redirection after verifying...

PT-2026-35087

Name of the Vulnerable Software and Affected Versions langchain-openai versions prior to 1.1.14 Description The url to size helper function, utilized by get num tokens from messages for image token counting, contains a Time-of-Check to Time-of-Use TOCTOU flaw. The function validates URLs for...

Anthropic MCP Design Vulnerability Enables RCE, Threatening AI Supply Chain

Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's MCP architecture that could pave the way for remote code execution and have a cascading effect on the artificial intelligence AI supply chain. "This flaw enables Arbitrary Command Execution R...

agent-builder (>=0.0.2 <=0.1.7), agentmanager (>=0.1.0 <=0.1.1) +48 more potentially affected by CVE-2026-41488 via langchain-openai (>=1.0.0 <=1.1.12)

langchain-openai PYPI version =1.0.0, =0.0.2, =0.1.0, =3.0.3, =0.0.48, =0.0.54, =0.1.2, =0.1.0, =0.1.0, =0.1.17rc1, =0.1.22 and more Source cves: CVE-2026-41488 Source advisory: SNYK:PYTHON-LANGCHAINOPENAI-16097112...