LangChain 路径遍历漏洞

LangChain is built as an application using LLM through composability. LangChain suffers from a path traversal vulnerability that stems from vulnerability to a path traversal attack, which can be exploited by an attacker to read or write a file anywhere on the filesystem, potentially leading to...

XML External Entity (XXE)

langchaincore is vulnerable to XML External Entity XXE. The vulnerability is due to the usage of the etree module from the XML parser within the XMLOutputParser component of LangChain, allowing attackers to inject malicious input into the XMLOutputParser...

GHSA-Q84M-RMW3-4382 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...

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...

CVE-2024-1455 Billion Laughs Attack leading to DoS in langchain-ai/langchain

A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity XXE exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading t...

CVE-2024-1455 Billion Laughs Attack leading to DoS in langchain-ai/langchain

A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity XXE exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading t...

CVE-2024-1455 Billion Laughs Attack leading to DoS in langchain-ai/langchain

A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity XXE exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive CPU and memory resources, leading t...

CVE-2024-1455

CVE-2024-1455 concerns a Billion Laughs Attack (XML External Entity) affecting the langchain-ai/langchain repository. Connected sources indicate the vulnerability centers on the XMLOutputParser using the standard Python etree XML parser, enabling an attacker to nest entities in XML to exhaust CPU...

LangChain 安全漏洞

LangChain builds applications using LLM through composability. A security vulnerability exists in LangChain that originates from allowing an attacker to generate a malicious payload for the parser via LLM, thereby compromising the availability of the service...

PT-2024-18059

Name of the Vulnerable Software and Affected Versions LangChain affected versions not specified Description The issue concerns the XMLOutputParser in LangChain, which utilizes the etree module from the XML parser in the standard Python library. This library has some XML vulnerabilities, making it...

LangChain directory traversal vulnerability

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

GHSA-H59X-P739-982C LangChain directory traversal vulnerability

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

CVE-2024-28088

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

Directory traversal

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

PYSEC-2024-43

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

PYSEC-2024-45

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

PYSEC-2024-43

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

PYSEC-2024-45

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

CVE-2024-28088

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a loadchain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure...

PT-2024-22256 · Langchain · Langchain

Name of the Vulnerable Software and Affected Versions: LangChain versions 0.1.10 and earlier Description: The issue allows an actor who can control the final part of the path parameter in a load chain call to perform ../ directory traversal. This bypasses the intended behavior of loading...