Lucene search
+L

7 matches found

PyPA
PyPA
•added 2026/07/13 3:46 p.m.•34 views

Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

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...

9.8CVSS6.1AI score0.00695EPSS
SaveExploits2References5Affected Software1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/07/10 12:00 a.m.•1 views

CVE-2026-55615: Improper Neutralization of Special Elements in Output Used by a Downstream Component

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, 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...

9.2CVSS5.8AI score0.00461EPSS
SaveExploits2References2
CVE
CVE
•added 2026/07/09 11:40 p.m.•66 views

CVE-2026-55615

Langroid CVE-2026-55615 affects the Neo4jChatAgent path, where LLM-generated Cypher queries are sent unvalidated to the Neo4j driver prior to version 0.65.5. Connected docs describe a prompt-injection risk enabling read/write/destroy of graph data and, with APOC or dbms.security, potential OS com...

9.2CVSS6AI score0.00461EPSS
SaveExploits2References2
OSV
OSV
•added 2026/07/09 11:40 p.m.•15 views

CVE-2026-55615 Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, 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...

9.2CVSS6.1AI score
SaveExploits0References4
attackerkb
attackerkb
•added 2026/07/09 11:40 p.m.•20 views

CVE-2026-55615

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, 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...

9.2CVSS6.1AI score0.00461EPSS
SaveExploits2References3Affected Software1
Cvelist
Cvelist
•added 2026/07/09 11:40 p.m.•54 views

CVE-2026-55615 Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, 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...

9.2CVSS0.00461EPSS
SaveExploits2References2
OSV
OSV
•added 2026/07/06 9:22 p.m.•40 views

GHSA-2PQ5-3Q89-J7CC Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

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...

9.2CVSS5.9AI score0.00461EPSS
SaveExploits2References2
Rows per page
Query Builder