CVE-2026-55615CWE-74

Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Critical · published July 9, 2026

CVSS v4.0
9.2
EPSS
0%
Percentile
39.0
In the wild
Unconfirmed
What it is

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.

The record
Technical detail
CVSS v4.0
9.2 · CRITICAL
Vector
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
EPSS
0.00461 · 39.0th percentile
Weakness
CWE-74 · Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
Published
2026-07-09T23:40Z
EPSS history
Timeline
  • 09 JUL 23:40Z
    Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879
    cvelistv5