dbcve.org
InjectionWeakness · CWE-74

CVE-2026-55615

CRITICAL · 9.2 CVSS v4.0 Published 2026-07-10
Patch available
A vendor patch is available. No clean upgrade release — apply the published patch.
See remediation →
100/100
Remediation priority · Urgent
Remotely reachable No privileges Zero-click Patch available 6 weeks old

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

Langroid's Neo4jChatAgent executes LLM-generated Cypher queries directly against the Neo4j driver without any validation, allowlisting, or opt-out mechanism. Attackers with prompt injection capability (via direct user input or RAG-retrieved content) can craft malicious Cypher to read or delete all graph data, and achieve OS command execution when Neo4j APOC or dbms.security procedures are enabled.

MitigationUpgrade to Langroid version 0.65.5 or later which implements query validation, statement-type allowlisting, and opt-out controls for the neo4j module.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
Authentication
X
User interaction
None
Scope
X

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify installed Langroid version
    Run 'pip show langroid' or check your requirements.txt/pipfile.lock for the langroid package version
    Affected if Version is lower than 0.65.5 (the vulnerable version range)
  2. Locate Neo4jChatAgent usage in your codebase
    Search for imports or references to 'Neo4jChatAgent' or 'neo4j' in your application code, configuration files, or documentation
    Affected if Neo4jChatAgent class is being instantiated or the neo4j module is imported in your project
  3. Verify Neo4j driver configuration
    Inspect your application's configuration for Neo4j connection settings (uri, credentials, database name) passed to the Neo4jChatAgent or Neo4j driver
    Affected if A Neo4j driver is configured and connected to a Neo4j database instance
  4. Check if Cypher query generation is enabled
    Review your Langroid agent configuration to confirm the Neo4jChatAgent is set up to generate and execute Cypher queries (this is the default behavior)
    Affected if The agent is configured to generate Cypher queries from LLM output without additional validation layers
  5. Inspect Neo4j database for APOC or dbms.security procedure availability
    Execute 'SHOW PROCEDURES' or 'SHOW PROCEDURES YIELD name' in Neo4j browser or client to list available procedures; check for 'apoc.*' or 'dbms.security.*' procedures
    Affected if APOC procedures or dbms.security procedures are enabled and available (enables OS command execution path)

Your environment is affected if you use Langroid versions before 0.65.5 with the Neo4jChatAgent enabled and connected to a Neo4j database, especially if APOC or dbms.security procedures are available in that database.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Patch available Apply the vendor patch
Vendor patch github.com →
Interim mitigation

Upgrade to Langroid version 0.65.5 or later which implements query validation, statement-type allowlisting, and opt-out controls for the neo4j module.

Recommended fix High confidence

langroid version 0.65.5

  1. Upgrade langroid to version 0.65.5 or later using your package manager (e.g., pip install langroid>=0.65.5)
  2. Verify the upgrade was successful by checking the installed version
  3. If using Neo4jChatAgent, confirm the fix includes proper Cypher query validation, statement-type allowlisting, or an opt-out gate as described in the security fix
Caveat Review release notes for 0.65.5 to check for any breaking changes or API modifications

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation3.0 h
  • Implementation6.0 h
  • Testing4.0 h
  • Review / QA2.0 h
15.0 hours of engineering $2,640
Get the patch applied

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,224.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-55615 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-55615 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data