Langroid has Prompt to SQL Injection, Leading to RCE

Security Vulnerability Report: Prompt to SQL Injection leading to RCE in latest Langroid Affected Scopelangroid 0.63.0 Vulnerability Description SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges...

MAI-2023-0001

Web applications that integrate Large Language Models LLMs using Langchain or similar middleware are susceptible to Prompt-to-SQL P2SQL injection attacks. This vulnerability arises when unsanitized user prompts are manipulated to compel the LLM to produce malicious SQL queries, thereby facilitati...