CVSS: 9.8EPSS: 3%CPEs: 1EXPL: 5CVE-2023-36281
https://notcve.org/view.php?id=CVE-2023-36281
An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt. This is related to __subclasses__ or a template. • https://github.com/tagomaru/CVE-2023-36281 https://github.com/miguelc49/CVE-2023-36281-2 https://github.com/miguelc49/CVE-2023-36281-1 https://aisec.today/LangChain-2e6244a313dd46139c5ef28cbcab9e55 https://github.com/hwchase17/langchain/issues/4394 https://github.com/langchain-ai/langchain/releases/tag/v0.0.312 • CWE-94: Improper Control of Generation of Code ('Code Injection') •
CVSS: 9.8EPSS: 0%CPEs: 1EXPL: 1CVE-2023-38860
https://notcve.org/view.php?id=CVE-2023-38860
An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter. Un problema en LangChain v.0.0.231 permite a un atacante remoto ejecutar código arbitrario a través del parámetro prompt. • https://github.com/hwchase17/langchain/issues/7641 • CWE-94: Improper Control of Generation of Code ('Code Injection') •
CVSS: 9.8EPSS: 0%CPEs: 1EXPL: 1CVE-2023-39659
https://notcve.org/view.php?id=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. Un problema en langchain langchain-ai v.0.0.232 y anteriores permite a un atacante remoto ejecutar código arbitrario a través de un script manipulado en el componente PythonAstREPLTool._run. • https://github.com/langchain-ai/langchain/issues/7700 https://github.com/langchain-ai/langchain/pull/5640 • CWE-74: Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') •
CVSS: 9.8EPSS: 0%CPEs: 1EXPL: 1CVE-2023-38896
https://notcve.org/view.php?id=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 from_math_prompt and from_colored_object_prompt functions. Un problema en langchain v.0.0.194 de Harrison Chase y anteriores permite a un atacante remoto ejecutar código arbitrario a través de las funciones from_math_prompt y from_colored_object_prompt. • https://github.com/hwchase17/langchain/issues/5872 https://github.com/hwchase17/langchain/pull/6003 https://twitter.com/llm_sec/status/1668711587287375876 • CWE-74: Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') •
CVSS: 9.8EPSS: 0%CPEs: 1EXPL: 1CVE-2023-36095
https://notcve.org/view.php?id=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 from_math_prompt and from_colored_object_prompt. • http://langchain.com https://github.com/hwchase17/langchain https://github.com/langchain-ai/langchain/issues/5872 • CWE-94: Improper Control of Generation of Code ('Code Injection') •