PYSEC-2026-1648 MLFlow unsafe deserialization

Deserialization of untrusted data can occur in versions of the MLflow platform running version 2.5.0 or newer, enabling a maliciously uploaded Langchain AgentExecutor model to run arbitrary code on an end user’s system when interacted with...

PYSEC-2026-1510 langchain vulnerable to path traversal

langchain-ai/langchain is vulnerable to path traversal due to improper limitation of a pathname to a restricted directory 'Path Traversal' in its LocalFileStore functionality. An attacker can leverage this vulnerability to read or write files anywhere on the filesystem, potentially leading to...

PYSEC-2026-1519 LangChain's XMLOutputParser vulnerable to XML Entity Expansion

The XMLOutputParser in LangChain uses the etree module from the XML parser in the standard python library which has some XML vulnerabilities; see: https://docs.python.org/3/library/xml.html This primarily affects users that combine an LLM or agent with the XMLOutputParser and expose the component...

PYSEC-2026-1509 langchain Server-Side Request Forgery vulnerability

With the following crawler configuration: python from bs4 import BeautifulSoup as Soup url = "https://example.com" loader = RecursiveUrlLoader url=url, maxdepth=2, extractor=lambda x: Soupx, "html.parser".text docs = loader.load An attacker in control of the contents of https://example.com could...

PYSEC-2026-1508 Langchain Server-Side Request Forgery vulnerability

In Langchain before 0.0.329, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks...

Langchain Server-Side Request Forgery vulnerability

In Langchain before 0.0.329, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks...

CVE-2026-14742 langchain-ai langgraph Task Result Cache _cache.py _freeze weak hash

A vulnerability was determined in langchain-ai langgraph up to 1.2.4. The affected element is the function freeze of the file libs/langgraph/langgraph/internal/cache.py of the component Task Result Cache. This manipulation of the argument defaultcachekey causes use of weak hash. The attack is...

CVE-2026-14742

The CVE affects langchain-ai langgraph up to 1.2.4. The vulnerability lies in the function _freeze in libs/langgraph/langgraph/_internal/_cache.py (Task Result Cache). Manipulating the argument default_cache_key causes use of a weak hash, enabling a possible remote attack. Exploitation is describ...

Security Bulletin: Maximo AI Service uses multiple third party dependencies which are vulnerable to multiple CVEs.

Summary Maximo AI Service uses pdfminersix-20251107-py3-none-any.whl, requests-2.32.5-py3-none-any.whl, langchaincore-0.3.81-py3-none-any.whl, pythondotenv-1.0.1-py3-none-any.whl, langchaintextsplitters-0.3.11-py3-none-any.whl, qs-6.15.1.tgz, idna-3.10-py3-none-any.whl, idna-3.14-py3-none-any.whl...

PYSEC-2026-372 Langchain SQL Injection vulnerability

In Langchain before 0.0.247, prompt injection allows execution of arbitrary code against the SQL service provided by the chain...

PYSEC-2026-374 LangChain Experimental Eval Injection vulnerability

langchainexperimental aka LangChain Experimental 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify which uses eval in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 2023-10-05...

PYSEC-2026-375 LangChain Experimental vulnerable to arbitrary code execution

langchainexperimental aka LangChain Experimental before 0.0.52, part of LangChain before 0.1.8, allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the import, subclasses, builtins, globals, getattribute, bases, mro, or base attribute in Python code. These are not...

LangChain < 1.3.9 Path Traversal (CVE-2026-55443)

The version of LangChain installed on the remote host is prior to 1.3.9. It is, therefore, affected by a path traversal vulnerability: - Several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root director...

CVE-2026-12866

A flaw was found in expr-eval. A remote attacker can exploit this vulnerability by supplying crafted expressions to the toJSFunction API. These expressions are then compiled into native code using new Function, allowing the attacker to execute arbitrary JavaScript code. This can lead to arbitrary...

PYSEC-2026-2192

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search...

CVE-2026-55443

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search...

CVE-2026-55443 LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search...

CVE-2026-55443

CVE-2026-55443 describes a path traversal / sandbox-escape flaw in LangChain prior to 1.3.9. The vulnerability arises when components that resolve filesystem paths or expand search patterns fail to confine results to a trusted root, allowing untrusted inputs (paths, globs, symlinks, or LLM-influe...

CVE-2026-55443 LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search...

EUVD-2026-38332

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search...