PT-2025-47809

Name of the Vulnerable Software and Affected Versions LangChain versions 0.3.79 and prior LangChain versions 1.0.0 through 1.0.6 Description LangChain is a framework used for building agents and applications powered by Large Language Models LLMs. A template injection issue exists in the prompt...

EUVD-2024-17468

Malicious code in bioql PyPI...

LLMs Cannot Reliably Judge (Yet?): a Comprehensive Assessment on the Robustness of LLM-As-A-Judge

Large Language Models LLMs have demonstrated remarkable intelligence across various tasks, which has inspired the development and widespread adoption of LLM-as-a-Judge systems for automated model testing, such as red teaming and benchmarking. However, these systems are susceptible to adversarial...

CVE-2024-10940

A vulnerability in langchain-core versions =0.1.17,=0.2.0,=0.3.0,0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability to create langchaincore.prompts.ImagePromptTemplate's and by extension langchaincore.prompts.ChatPromptTemplate's...

PT-2024-38718 · Unknown · Gaizhenbiao/Chuanhuchatgpt

Name of the Vulnerable Software and Affected Versions: gaizhenbiao/chuanhuchatgpt version 20240628 Description: An arbitrary file read issue exists due to insufficient validation when loading prompt template files. An attacker can read any file that matches specific criteria using an absolute pat...

CVE-2024-1741

lunary-ai/lunary version 1.0.1 is vulnerable to improper authorization, allowing removed members to read, create, modify, and delete prompt templates using an old authorization token. Despite being removed from an organization, these members can still perform operations on prompt templates by...

CVE-2024-1741

lunary-ai/lunary version 1.0.1 is vulnerable to improper authorization, allowing removed members to read, create, modify, and delete prompt templates using an old authorization token. Despite being removed from an organization, these members can still perform operations on prompt templates by...

CVE-2024-1741 Improper Authorization in lunary-ai/lunary

lunary-ai/lunary version 1.0.1 is vulnerable to improper authorization, allowing removed members to read, create, modify, and delete prompt templates using an old authorization token. Despite being removed from an organization, these members can still perform operations on prompt templates by...

CVE-2024-1741

CVE-2024-1741 affects lunary-ai/lunary v1.0.1, with an improper authorization flaw enabling removed members to read, create, modify, and delete prompt templates by reusing an old authorization token. The issue allows operations on prompt templates despite removal from an organization, via HTTP re...

PT-2024-18266 · Lunary Ai · Lunary

Name of the Vulnerable Software and Affected Versions: lunary-ai/lunary version 1.0.1 Description: The issue allows removed members to read, create, modify, and delete prompt templates using an old authorization token. Despite being removed from an organization, these members can still perform...