+ "details": "### Summary\n\nGraphiti 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.\n\nIn 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.\n\nAffected 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.\n\nThis issue was mitigated in `0.28.2`.\n\n### Affected Versions\n\n- `0.28.1` and earlier\n\n### Fixed Version\n\n- `0.28.2`\n\n### Affected Components\n\n- Graphiti Core search filter construction\n- Graphiti MCP Server `search_nodes` when used by an LLM client processing untrusted prompts\n\n### Technical Details\n\nBefore `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.\n\nThe vulnerable logic was effectively:\n\n- `node_labels = '|'.join(filters.node_labels)`\n- `node_label_filter = 'n:' + node_labels`\n\nThe same pattern was also used in edge-search filter construction.\n\nIn 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`.\n\n### Impact\n\nSuccessful exploitation could allow arbitrary Cypher execution within the privileges of the configured graph database connection, including:\n\n- reading graph data outside the intended search scope\n- modifying graph data\n- deleting graph data\n- bypassing logical group isolation enforced at the query layer\n\n### Additional Note on `group_ids`\n\nSeparately, 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`.\n\n### Mitigation\n\nUpgrade to `0.28.2` or later.\n\nVersion `0.28.2` added:\n\n- validation of `SearchFilters.node_labels`\n- defense-in-depth label validation in shared search-filter constructors\n- validation of entity node labels in persistence query builders\n- validation of `group_ids` in shared search fulltext helpers\n\n### Workarounds\n\nIf you cannot upgrade immediately:\n\n- do not expose Graphiti MCP tools to untrusted users or to LLM workflows that process untrusted prompt content\n- avoid passing untrusted values into `SearchFilters.node_labels` or MCP `entity_types`\n- restrict graph database credentials to the minimum privileges required\n\n### Credits\n\n@4n93L for their original report.",
![advisory-database[bot]](https://avatars.githubusercontent.com/in/21409?v=4&size=40){kind=avatar}
0 commit comments