Flexible GraphRAG is a Python framework for building graph and retrieval-augmented generation applications across multiple graph, vector, and search backends. From 0.6.0 until 0.8.2, the _escape() helper in flexible-graphrag/langchain/graph/pg_store_adapters/falkordb_adapter.py escapes quotes before backslashes and then interpolates the result into Cypher assembled by FalkorDBAdapter.add_graph_documents, allowing an inserted escape to be doubled and a quote to terminate the string early. When GRAPH_BACKEND=langchain and GRAPH_DB=falkordb are configured, attacker-influenced ingested document content can cause the extraction model to produce malicious entity or relationship values that reach these queries, allowing injected Cypher clauses to modify or delete graph data and, when the calling code surfaces query results to the user or LLM, disclose graph data. Dynamic node and relationship type identifiers are also inserted into backtick-quoted query positions without safe parameterization. The LlamaIndex FalkorDB store is not affected. This issue is fixed in version 0.8.2.
History

Tue, 10 Nov 2026 21:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}


Fri, 23 Oct 2026 00:45:00 +0000

Type Values Removed Values Added
First Time appeared Stevereiner
Stevereiner flexible-graphrag
Vendors & Products Stevereiner
Stevereiner flexible-graphrag

Thu, 22 Oct 2026 15:00:00 +0000

Type Values Removed Values Added
Description Flexible GraphRAG is a Python framework for building graph and retrieval-augmented generation applications across multiple graph, vector, and search backends. From 0.6.0 until 0.8.2, the _escape() helper in flexible-graphrag/langchain/graph/pg_store_adapters/falkordb_adapter.py escapes quotes before backslashes and then interpolates the result into Cypher assembled by FalkorDBAdapter.add_graph_documents, allowing an inserted escape to be doubled and a quote to terminate the string early. When GRAPH_BACKEND=langchain and GRAPH_DB=falkordb are configured, attacker-influenced ingested document content can cause the extraction model to produce malicious entity or relationship values that reach these queries, allowing injected Cypher clauses to modify or delete graph data and, when the calling code surfaces query results to the user or LLM, disclose graph data. Dynamic node and relationship type identifiers are also inserted into backtick-quoted query positions without safe parameterization. The LlamaIndex FalkorDB store is not affected. This issue is fixed in version 0.8.2.
Title Flexible GraphRAG: Cypher/Graph Injection via broken string-escaping in FalkorDB adapter (_escape()) - full graph wipe from ingested-document content
Weaknesses CWE-116
CWE-943
References
Metrics cvssV3_1

{'score': 7.1, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H'}


cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published: 2026-10-22T14:46:52.353Z

Updated: 2026-10-30T19:16:29.340Z

Reserved: 2026-10-21T16:15:06.492Z

Link: CVE-2026-114510

cve-icon Vulnrichment

Updated: 2026-10-30T19:16:24.903Z

cve-icon NVD

Status : Awaiting Analysis

Published: 2026-10-22T15:17:05.500

Modified: 2026-10-30T20:17:00.030

Link: CVE-2026-114510

cve-icon Redhat

No data.