CVE-2023-38860

An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter...

PT-2023-26641 · Langchain · Langchain

Name of the Vulnerable Software and Affected Versions: LangChain versions 0.0.231 through 0.0.246 Description: An issue in LangChain allows a remote attacker to execute arbitrary code via the prompt parameter. This enables the attacker to potentially gain control over the system, leading to sever...

CVE-2023-39659

An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool.run component...

CVE-2023-39659

LangChain is affected by an arbitrary code execution vulnerability in the PythonAstREPLTool._run path, exploitable in LangChain-AI releases before a fixed version. Affected: LangChain before 0.0.325 (per OSV/GHSA) and NVD notes v0.0.232 and earlier. Root cause: improper neutralization of user-sup...

LangChain Code Injection Vulnerability

LangChain is used to build applications using LLM through composability. A security vulnerability exists in LangChain version v.0.0.231 that originates from allowing remote attackers to execute arbitrary code via a prompt parameter...

CVE-2023-39659

An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool.run component...

CVE-2023-38896

An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the frommathprompt and fromcoloredobjectprompt functions...

LangChain Injection Vulnerability

LangChain is an application built using LLM through composability. A security vulnerability exists in LangChain version v.0.0.232, which originates from arbitrary code execution via the PythonAstREPLTool.run component...

CVE-2023-38860

An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter...

CVE-2023-39659

An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool.run component...

CVE-2023-38896

An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the frommathprompt and fromcoloredobjectprompt functions...

The vulnerability of the framework for creating applications based on the combination of language models (LLMs) like LangChain arises from the lack of protective measures for SQL query structures. This allows attackers to gain unauthorized access to protected information.

The vulnerability of the framework for creating applications based on the combination of language models LLMs like LangChain relates to the lack of measures taken to protect SQL query structures. Exploiting this vulnerability can allow a malicious actor, operating remotely, to gain unauthorized...

Arbitrary Code Execution

langchain is vulnerable to Arbitrary Code Execution. The vulnerability exists in the frommathprompt function at langchain.chains.PALChain which allows an attacker to execute arbitrary codes through prompt injection...

langchain Code Injection vulnerability

An issue in Harrison Chase langchain allows an attacker to execute arbitrary code via the PALChain,frommathpromptllm.run in the python exec method...

GHSA-GWQQ-6VQ7-5J86 langchain Code Injection vulnerability

An issue in Harrison Chase langchain allows an attacker to execute arbitrary code via the PALChain,frommathpromptllm.run in the python exec method...

agent-actors (=0.1.0), agent-reader (>=0.2.1 <=0.2.2) +162 more potentially affected by CVE-2023-36095 via langchain (>=0.0.100 <=0.0.235)

langchain PYPI version =0.0.100, =0.2.1, =0.1.0, =0.1.5, =0.0.1, =0.0.1, =0.0.1, =0.0.5, =0.0.14, =0.1.9, =0.0.33, =0.1.0a0, =0.2.0, =0.1.3, =0.1.5 and more Source cves: CVE-2023-36095 Source advisory: OSV:GHSA-GWQQ-6VQ7-5J86...

CVE-2023-36095

An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALChain, affected functions include frommathprompt and fromcoloredobjectprompt...

CVE-2023-36095

An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALChain, affected functions include frommathprompt and fromcoloredobjectprompt...

agent-actors (=0.1.0), agent-reader (>=0.2.1 <=0.2.2) +162 more potentially affected by CVE-2023-36095 via langchain (>=0.0.100 <=0.0.235)

langchain PYPI version =0.0.100, =0.2.1, =0.1.0, =0.1.5, =0.0.1, =0.0.1, =0.0.1, =0.0.5, =0.0.14, =0.1.9, =0.0.33, =0.1.0a0, =0.2.0, =0.1.3, =0.1.5 and more Source cves: CVE-2023-36095 Source advisory: OSV:PYSEC-2023-138...

Design/Logic Flaw

An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALChain, affected functions include frommathprompt and fromcoloredobjectprompt...