Skip to content

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 severity GitHub Reviewed Published Jun 15, 2026 in langroid/langroid • Updated Jul 6, 2026

Package

pip langroid (pip)

Affected versions

<= 0.65.4

Patched versions

0.65.5

Description

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.

Technical detail

Untrusted-input to sink trace (reviewed on langroid HEAD b9df06f, v0.65.3):

  1. Tool schemas accept raw query text from the LLM. langroid/agent/special/neo4j/tools.py:4-9 (CypherRetrievalTool.cypher_query: str) and :15-21 (CypherCreationTool.cypher_query: str). These tools are enabled unconditionally in neo4j_chat_agent.py:412-419 (enable_message([GraphSchemaTool, CypherRetrievalTool, CypherCreationTool, DoneTool])).

  2. Read path. neo4j_chat_agent.py:300 cypher_retrieval_tool(msg) -> :325 query = msg.cypher_query -> :328 self.read_query(query) -> :223 session.run(query, parameters). The LLM-controlled string is the first positional argument to session.run; parameters is None. No validation occurs between :325 and :223.

  3. Write path. neo4j_chat_agent.py:338 cypher_creation_tool(msg) -> :348 query = msg.cypher_query -> :351 self.write_query(query) -> :276 session.write_transaction(lambda tx: tx.run(query, parameters)). The only inspection of the string (write_query :251-264) is a query.upper() substring test for CREATE/MERGE/CONSTRAINT/INDEX whose sole effect is setting self.config.database_created = True; it blocks nothing. A query such as MATCH (n) DETACH DELETE n (the same statement the built-in remove_database helper runs at :287-293) passes unrestricted.

  4. Guarded-sibling contrast proving the incomplete fix. The SQLChatAgent, patched for the parent CVE, validates every query before execution. langroid/agent/special/sql/sql_chat_agent.py:256 defines allow_dangerous_operations: bool = False (opt-in gate); :618 _validate_query runs (a) a dangerous-pattern regex blocklist (_DANGEROUS_SQL_PATTERNS, :628-641), (b) a sqlglot statement-type allowlist defaulting to SELECT-only (:643-686), and (c) an AST-level dangerous-function blocklist (:687-704). run_query calls rejection = self._validate_query(query) at :721 before executing. The neo4j read_query/write_query paths have no equivalent: a grep for _validate_query/allow_dangerous in neo4j_chat_agent.py returns nothing. The defense exists for SQL and is simply absent for Cypher, which is the definition of an incomplete fix for the same prompt-to-query-language injection class.

Proof of concept (static, no third-party systems, no live Neo4j required)

Step 1 (presence vs absence of the guard, one command):

grep -n "_validate_query\|allow_dangerous" langroid/agent/special/sql/sql_chat_agent.py    # SQL: many hits (gate + validator + call site :721)
grep -n "_validate_query\|allow_dangerous" langroid/agent/special/neo4j/neo4j_chat_agent.py # neo4j: ZERO hits

Step 2 (sink trace is direct, no interposed check):

read_query:  msg.cypher_query (line 325) -> read_query(query) (328) -> session.run(query, parameters) (223)
write_query: msg.cypher_query (348) -> write_query(query) (351) -> tx.run(query, parameters) (276)

The only string inspection (write_query 251-264) is a .upper() substring test that only sets database_created=True and rejects nothing. The asymmetry (validator + opt-out gate enforced on every SQL query at sql_chat_agent.py:721; nothing on either Cypher path) is the deterministic artifact: the same project, for the same injection class, guards one query language and not the other. A dynamic confirmation against an operator-owned disposable Neo4j (create a CSPRNG-marked node via cypher_creation_tool, read it back via cypher_retrieval_tool, then DETACH DELETE it) reproduces the read/write/destroy primitive without any third-party system.

Impact

An attacker who can influence the agent prompt (directly, or indirectly via content the agent reads back through RAG) controls the executed Cypher. Floor (no extra config, not contingent): unauthorized read of all graph data via cypher_retrieval_tool and full write/destroy (including MATCH (n) DETACH DELETE n) via cypher_creation_tool, plus the built-in LOAD CSV remote-fetch (SSRF) primitive. Ceiling (config-conditional, when APOC / dbms.security procedures are granted to the DB role, a common deployment): apoc.load.* (SSRF + remote/local file read), apoc.cypher.runFile / apoc.import.* / apoc.export.* (filesystem), and CALL dbms.* admin procedures, i.e. the Cypher analogue of the parent's COPY ... FROM PROGRAM RCE primitive. This mirrors the privileged-role contingency the parent advisory (CVE-2026-25879) accepted.

Suggested fix

Mirror the SQLChatAgent fix in the neo4j module: (1) add allow_dangerous_operations: bool = False to Neo4jChatAgentConfig with a read-only default for cypher_retrieval_tool; (2) add a _validate_cypher(query, write) method that, unless allow_dangerous_operations is True, blocks CALL apoc., CALL dbms., CALL db.* admin procedures, LOAD CSV, and any procedure/function touching filesystem/network/OS, and (for the read path) rejects write clauses (CREATE/MERGE/SET/DELETE/DETACH DELETE/REMOVE/DROP); (3) enforce it before session.run (read_query :223) and tx.run (write_query :276), returning the rejection to the LLM the way run_query does at sql_chat_agent.py:721; (4) document, as the SQL config does, that LLM-generated Cypher is prompt-injectable and that allow_dangerous_operations should only be set with a least-privilege Neo4j role. I am happy to send this as a PR if useful.

Relationship to the parent advisory

GHSA-mxfr-6hcw-j9rq / CVE-2026-25879 (Langroid SQLChatAgent prompt-to-SQL injection leading to RCE; Critical; fixed 0.63.0, SQLChatAgent only). This report is the same injection class in the still-unpatched sibling Neo4jChatAgent.

Severity note (honest, both ways)

Filed as High to reflect the non-contingent floor (unrestricted attacker-steered graph read/write/destroy + LOAD CSV SSRF, present regardless of APOC). The ceiling is Critical and RCE-equivalent when APOC / admin procedures are enabled on the DB role, at parity with the parent CVE-2026-25879 which was rated Critical under an equivalent privileged-role contingency. Please rate per your deployment assumptions.

Resolution (maintainer)

Fixed in 0.65.5. Both Neo4jChatAgent (Cypher) and the sibling ArangoChatAgent (AQL, raised in the follow-up) now mirror the SQLChatAgent controls: a new allow_dangerous_operations config gate (default False), with the retrieval tool restricted to read-only queries and both tools rejecting code-execution / file / network primitives (LOAD CSV, apoc.*, dbms.*, CALL db.* for Cypher; user-defined namespace::func calls for AQL) unless the operator opts in. Validation is enforced at the tool handlers, so internal schema/maintenance calls are unaffected. Upgrade to 0.65.5 and run the agents against a least-privilege database role.

References

@pchalasani pchalasani published to langroid/langroid Jun 15, 2026
Published to the GitHub Advisory Database Jul 6, 2026
Reviewed Jul 6, 2026
Last updated Jul 6, 2026

Severity

Critical

CVSS overall score

This score calculates overall vulnerability severity from 0 to 10 and is based on the Common Vulnerability Scoring System (CVSS).
/ 10

CVSS v4 base metrics

Exploitability Metrics
Attack Vector Network
Attack Complexity Low
Attack Requirements Present
Privileges Required None
User interaction None
Vulnerable System Impact Metrics
Confidentiality High
Integrity High
Availability High
Subsequent System Impact Metrics
Confidentiality None
Integrity None
Availability None

CVSS v4 base metrics

Exploitability Metrics
Attack Vector: This metric reflects the context by which vulnerability exploitation is possible. This metric value (and consequently the resulting severity) will be larger the more remote (logically, and physically) an attacker can be in order to exploit the vulnerable system. The assumption is that the number of potential attackers for a vulnerability that could be exploited from across a network is larger than the number of potential attackers that could exploit a vulnerability requiring physical access to a device, and therefore warrants a greater severity.
Attack Complexity: This metric captures measurable actions that must be taken by the attacker to actively evade or circumvent existing built-in security-enhancing conditions in order to obtain a working exploit. These are conditions whose primary purpose is to increase security and/or increase exploit engineering complexity. A vulnerability exploitable without a target-specific variable has a lower complexity than a vulnerability that would require non-trivial customization. This metric is meant to capture security mechanisms utilized by the vulnerable system.
Attack Requirements: This metric captures the prerequisite deployment and execution conditions or variables of the vulnerable system that enable the attack. These differ from security-enhancing techniques/technologies (ref Attack Complexity) as the primary purpose of these conditions is not to explicitly mitigate attacks, but rather, emerge naturally as a consequence of the deployment and execution of the vulnerable system.
Privileges Required: This metric describes the level of privileges an attacker must possess prior to successfully exploiting the vulnerability. The method by which the attacker obtains privileged credentials prior to the attack (e.g., free trial accounts), is outside the scope of this metric. Generally, self-service provisioned accounts do not constitute a privilege requirement if the attacker can grant themselves privileges as part of the attack.
User interaction: This metric captures the requirement for a human user, other than the attacker, to participate in the successful compromise of the vulnerable system. This metric determines whether the vulnerability can be exploited solely at the will of the attacker, or whether a separate user (or user-initiated process) must participate in some manner.
Vulnerable System Impact Metrics
Confidentiality: This metric measures the impact to the confidentiality of the information managed by the VULNERABLE SYSTEM due to a successfully exploited vulnerability. Confidentiality refers to limiting information access and disclosure to only authorized users, as well as preventing access by, or disclosure to, unauthorized ones.
Integrity: This metric measures the impact to integrity of a successfully exploited vulnerability. Integrity refers to the trustworthiness and veracity of information. Integrity of the VULNERABLE SYSTEM is impacted when an attacker makes unauthorized modification of system data. Integrity is also impacted when a system user can repudiate critical actions taken in the context of the system (e.g. due to insufficient logging).
Availability: This metric measures the impact to the availability of the VULNERABLE SYSTEM resulting from a successfully exploited vulnerability. While the Confidentiality and Integrity impact metrics apply to the loss of confidentiality or integrity of data (e.g., information, files) used by the system, this metric refers to the loss of availability of the impacted system itself, such as a networked service (e.g., web, database, email). Since availability refers to the accessibility of information resources, attacks that consume network bandwidth, processor cycles, or disk space all impact the availability of a system.
Subsequent System Impact Metrics
Confidentiality: This metric measures the impact to the confidentiality of the information managed by the SUBSEQUENT SYSTEM due to a successfully exploited vulnerability. Confidentiality refers to limiting information access and disclosure to only authorized users, as well as preventing access by, or disclosure to, unauthorized ones.
Integrity: This metric measures the impact to integrity of a successfully exploited vulnerability. Integrity refers to the trustworthiness and veracity of information. Integrity of the SUBSEQUENT SYSTEM is impacted when an attacker makes unauthorized modification of system data. Integrity is also impacted when a system user can repudiate critical actions taken in the context of the system (e.g. due to insufficient logging).
Availability: This metric measures the impact to the availability of the SUBSEQUENT SYSTEM resulting from a successfully exploited vulnerability. While the Confidentiality and Integrity impact metrics apply to the loss of confidentiality or integrity of data (e.g., information, files) used by the system, this metric refers to the loss of availability of the impacted system itself, such as a networked service (e.g., web, database, email). Since availability refers to the accessibility of information resources, attacks that consume network bandwidth, processor cycles, or disk space all impact the availability of a system.
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 score

Exploit Prediction Scoring System (EPSS)

This score estimates the probability of this vulnerability being exploited within the next 30 days. Data provided by FIRST.
(37th percentile)

Weaknesses

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component. Learn more on MITRE.

CVE ID

CVE-2026-55615

GHSA ID

GHSA-2pq5-3q89-j7cc

Source code

Credits

Loading Checking history
See something to contribute? Suggest improvements for this vulnerability.