Summary
Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879
Full technical 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):
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 inneo4j_chat_agent.py:412-419(enable_message([GraphSchemaTool, CypherRetrievalTool, CypherCreationTool, DoneTool])).Read path.
neo4j_chat_agent.py:300cypher_retrieval_tool(msg) ->:325query = msg.cypher_query ->:328self.read_query(query) ->:223session.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.Write path.
neo4j_chat_agent.py:338cypher_creation_tool(msg) ->:348query = msg.cypher_query ->:351self.write_query(query) ->:276session.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 asMATCH (n) DETACH DELETE n(the same statement the built-in remove_database helper runs at :287-293) passes unrestricted.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:256defines 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:721before 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.
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.
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.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
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.
Frequently Asked Questions
- What is CVE-2026-55615? CVE-2026-55615 is a critical-severity security vulnerability in langroid (pip), affecting versions <= 0.65.4. It is fixed in 0.65.5.
- Which versions of langroid are affected by CVE-2026-55615? langroid (pip) versions <= 0.65.4 is affected.
- Is there a fix for CVE-2026-55615? Yes. CVE-2026-55615 is fixed in 0.65.5. Upgrade to this version or later.
- Is CVE-2026-55615 exploitable, and should I be worried? Whether CVE-2026-55615 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-55615 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-55615? Upgrade
langroidto 0.65.5 or later.