Advisory record · GHSA-2pq5-3q89-j7cc

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

CVSS 9.2 CriticalCriticalEPSS 0.0046 · 40th percentile

Critical, because:

  • CVSS score 9.2: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 6 Jul 2026, 21:22 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
langroidPyPI<0.65.50.65.5
Identifiers
GHSA-2pq5-3q89-j7cc · CVE-2026-55615 · PYSEC-2026-2576
Weakness (CWE)
CWE-74
Published
6 Jul 2026
Updated
13 Jul 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

Langroid versions before 0.65.5 have a flaw in Neo4jChatAgent, which passes LLM-generated Cypher queries directly to the Neo4j driver without validation. An attacker who can influence the agent's prompt, directly or through content retrieved via RAG, can read, modify, or delete graph data, and where APOC or dbms procedures are enabled on the server, may gain OS command or filesystem access. Upgrade to langroid 0.65.5, which adds a default-off allow_dangerous_operations gate and validation of Cypher tool queries.

Written 6 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
9.2 Critical 4.0 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 CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0046, the 40th percentile, on 13 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 15:02 UTC First seen by agentprime
  2. 31 Oct 2026, 15:02 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.