CVE-2026-55615
CriticalCVSS 9.2Exploitation Probability (EPSS)
Low risk37th percentile - higher than 37% of all known CVEs
Summary
Langroid before version 0.65.5 has a vulnerability in the Neo4jChatAgent component that allows Cypher query injection. An attacker can influence the query via prompt injection, enabling reading or destroying all graph data, and with APOC or dbms.security procedures enabled, achieving OS command and filesystem access.
Risk Assessment
The risk for the organization includes complete loss of confidentiality and integrity of Neo4j data and potential server takeover, which can lead to escalation of attacks across the entire IT infrastructure.
Recommendation
Immediately update Langroid to version 0.65.5 or later, which contains a fix for the neo4j module. Additionally, consider restricting Neo4j database user privileges and disabling unnecessary APOC and dbms.security procedures.
Original NVD description (English source)
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.