CyberRota Analysis
AI-GeneratedThe Langroid framework, specifically the Neo4jChatAgent prior to version 0.65.5, is vulnerable due to the lack of validation for LLM-generated Cypher queries, allowing attackers to exploit prompt injection to manipulate queries. This vulnerability can lead to unauthorized access, enabling attackers to read or delete graph data and potentially execute OS commands if certain procedures are enabled. Organizations using Langroid with the affected version should prioritize upgrading to version 0.65.5 to mitigate these risks.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt injection (direct user input or indirect content the agent reads back via RAG), so an attacker who can influence the prompt can read or destroy all graph data and, when APOC or dbms.security procedures are enabled on the server, achieve OS-command and filesystem access. This is the same defect class and threat model as the SQLChatAgent prompt-to-SQL-to-RCE issue fixed in version 0.63.0 (CVE-2026-25879); that fix did not extend to the neo4j module. Version 0.65.5 contains a fix for the neo4j module.