CVE-2026-44843: high-severity vulnerability in langchain-ai langchain
LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
21Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 8.2epss 0.4%
LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects="all". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
Affected products
langchain-ai · langchainRelated CVEs — langchain-ai langchain
In the same product, most dangerous first.
CVE-2025-68664CRITICALLangChain serialization injection vulnerability enables secret extraction in dumps/loads APIsEPSS 42.9%CVE-2026-34070HIGHLangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functionsEPSS 1.5%CVE-2025-65106HIGHLangChain Vulnerable to Template Injection via Attribute Access in Prompt TemplatesEPSS 0.5%CVE-2026-26013LOWLangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messagesEPSS 0.4%CVE-2026-40087MEDIUMLangChain has incomplete f-string validation in prompt templatesEPSS 0.3%CVE-2026-55443MEDIUMLangChain: Path traversal and sandbox escape in LangChain file-search middleware and loadersEPSS 0.2%