Vulnerability 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.
Related Weaknesses (CWE)
References
- https://github.com/langroid/langroid/commit/5a3097d9dd6378b08ced5480b0caf76cc58d
- https://github.com/langroid/langroid/security/advisories/GHSA-2pq5-3q89-j7cc
- https://github.com/langroid/langroid/security/advisories/GHSA-2pq5-3q89-j7cc
FAQ
What is CVE-2026-55615?
CVE-2026-55615 is a documented vulnerability. 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 validat...
How severe is CVE-2026-55615?
CVSS scoring is not yet available for CVE-2026-55615. Check NVD for updates.
Is there a patch for CVE-2026-55615?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.