graphiti-core
Affected
- introduced
0, fixed0.28.2(ecosystem)
Fixed versions
0.28.2
Fix
- Fixed version
0.28.2pip install --upgrade graphiti-core==0.28.2
Advisory
Also known as: CVE-2026-32247, GHSA-gg5m-55jj-8m5g
Graphiti vulnerable to Cypher Injection via unsanitized node_labels in search filters
Summary
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.
Affected Versions
0.28.1 and earlierFixed Version
0.28.2Affected Components
search_nodes when used by an LLM client processing untrusted promptsTechnical Details
Before 0.28.2, Graphiti joined SearchFilters.node_labels with | and inserted the result directly into Cypher label expressions in the shared search-filter constructors used by non-Kuzu providers.
The vulnerable logic was effectively:
node_labels = '|'.join(filters.node_labels)node_label_filter = 'n:' + node_labelsThe same pattern was also used in edge-search filter construction.
In MCP deployments, search_nodes accepted an entity_types argument and passed it directly to SearchFilters(node_labels=entity_types). An attacker who could influence prompts processed by an LLM client with Graphiti MCP access could use prompt injection to steer the model into invoking search_nodes with crafted entity_types values containing Cypher syntax. Those values would then be interpolated into Cypher before 0.28.2.
Impact
Successful exploitation could allow arbitrary Cypher execution within the privileges of the configured graph database connection, including:
Additional Note on group_ids
Separately, the original report also identified a narrower issue in fulltext search query construction for unvalidated group_ids. That issue was distinct from the Cypher label-injection path described above and was also mitigated in 0.28.2.
Mitigation
Upgrade to 0.28.2 or later.
Version 0.28.2 added:
SearchFilters.node_labelsgroup_ids in shared search fulltext helpersWorkarounds
If you cannot upgrade immediately:
SearchFilters.node_labels or MCP entity_typesCredits
@4n93L for their original report.
High Basis: CVSS v3 score 8.1, vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
0, fixed 0.28.2 (ecosystem)0.28.2
0.28.2pip install --upgrade graphiti-core==0.28.2Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0