{"items":[{"id":"NVI-00017486","kind":"vulnerability","title":"Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-2pq5-3q89-j7cc","CVE-2026-55615"],"plain_summary":"GitHub lists this reviewed advisory for langroid. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-094da3aac4de611f0cfd9e1a606962cb"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-094da3aac4de611f0cfd9e1a606962cb","url":"https://github.com/advisories/GHSA-2pq5-3q89-j7cc","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-2pq5-3q89-j7cc","publisher":"GitHub Advisory Database","observed_at":"2026-11-04T23:36:01.427Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-094da3aac4de611f0cfd9e1a606962cb"],"technology":"langroid","known_exclusions":[],"conditions_summary":"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.\n\n## Technical detail\nUntrusted-input to sink trace (reviewed on langroid HEAD b9df06f, v0.65.3):\n\n1. 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 in `neo4j_chat_agent.py:412-419` (enable_message([GraphSchemaTool, CypherRetrievalTool, CypherCreationTool, DoneTool])).\n\n2. Read path. `neo4j_chat_agent.py:300` cypher_retrieval_tool(msg) -> `:325` query = msg.cypher_query -> `:","public_affected_ranges":["<= 0.65.4"]}],"null_published_at":"2026-11-05T19:10:21.396Z","source_updated_at":"2026-07-06T21:22:44.000Z","source_disclosed_at":"2026-07-06T21:22:43.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-04T23:36:01.427Z"}],"next_cursor":null,"snapshot_revision":"42594"}