CVE-2026-32247: Graphiti vulnerable to Cypher Injection via unsanitized node_labels in search filters
(updated )
Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.node_labels were concatenated directly into Cypher label expressions without validation.
In MCP deployments, this was exploitable not only through direct untrusted access to the Graphiti MCP server, but also through prompt injection against an LLM client that could be induced to call search_nodes with attacker-controlled entity_types values. The MCP server mapped entity_types to SearchFilters.node_labels, which then reached the vulnerable Cypher construction path.
Affected backends included Neo4j, FalkorDB, and Neptune. Kuzu was not affected by the label-injection issue because it used parameterized label handling rather than string-interpolated Cypher labels.
This issue was mitigated in 0.28.2.
References
- github.com/advisories/GHSA-gg5m-55jj-8m5g
- github.com/getzep/graphiti
- github.com/getzep/graphiti/commit/7d65d5e77e89a199a62d737634eaa26dbb04d037
- github.com/getzep/graphiti/pull/1312
- github.com/getzep/graphiti/releases/tag/v0.28.2
- github.com/getzep/graphiti/security/advisories/GHSA-gg5m-55jj-8m5g
- nvd.nist.gov/vuln/detail/CVE-2026-32247
Code Behaviors & Features
Detect and mitigate CVE-2026-32247 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →