CVE-2024-2057 – LangChain langchain_community TFIDFRetriever tfidf.py load_local server-side request forgery
https://notcve.org/view.php?id=CVE-2024-2057
A vulnerability was found in LangChain langchain_community 0.0.26. It has been classified as critical. Affected is the function load_local in the library libs/community/langchain_community/retrievers/tfidf.py of the component TFIDFRetriever. The manipulation leads to server-side request forgery. It is possible to launch the attack remotely. • https://github.com/bayuncao/vul-cve-16 https://github.com/bayuncao/vul-cve-16/tree/main/PoC.pkl https://github.com/langchain-ai/langchain/pull/18695 https://vuldb.com/?ctiid.255372 https://vuldb.com/?id.255372 • CWE-918: Server-Side Request Forgery (SSRF) •
CVE-2023-32786
https://notcve.org/view.php?id=CVE-2023-32786
In Langchain through 0.0.155, 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. En Langchain hasta 0.0.155, la inyección rápida permite a un atacante forzar al servicio a recuperar datos de una URL arbitraria, esencialmente proporcionando SSRF y potencialmente inyectando contenido en tareas posteriores. • https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1 • CWE-74: Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') •
CVE-2023-46229
https://notcve.org/view.php?id=CVE-2023-46229
LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an internal server. LangChain anterior a 0.0.317 permite SSRF a través de document_loaders/recursive_url_loader.py porque el rastreo puede proceder desde un servidor externo a un servidor interno. • https://github.com/langchain-ai/langchain/commit/9ecb7240a480720ec9d739b3877a52f76098a2b8 https://github.com/langchain-ai/langchain/pull/11925 • CWE-918: Server-Side Request Forgery (SSRF) •
CVE-2023-44467
https://notcve.org/view.php?id=CVE-2023-44467
langchain_experimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass the CVE-2023-36258 fix and execute arbitrary code via __import__ in Python code, which is not prohibited by pal_chain/base.py. langchain_experimental 0.0.14 permite a un atacante omitir la corrección CVE-2023-36258 y ejecutar código arbitrario a través de PALChain en el método python exec. • https://github.com/langchain-ai/langchain/commit/4c97a10bd0d9385cfee234a63b5bd826a295e483 •
CVE-2023-39631
https://notcve.org/view.php?id=CVE-2023-39631
An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary code via the evaluate function in the numexpr library. Un problema en LanChain-ai Langchain v.0.0.245 permite a un atacante remoto ejecutar código arbitrario a través de la función evaluate en numexpr library. • https://github.com/langchain-ai/langchain/issues/8363 https://github.com/pydata/numexpr/issues/442 • CWE-94: Improper Control of Generation of Code ('Code Injection') •