Signal is active with 2 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD description
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 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. Version 0.65.5 contains a fix for the neo4j module.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
AVAILABLE
Momentum
NONE
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 t… https://www.cve.org/CVERecord?id=CVE-2026-55615
Post summary
CVE‑2026‑55615 discloses that Langroid’s Neo4jChatAgent unvalidatedly executes LLM‑generated Cypher queries, creating a potential injection risk, but no PoC, exploit, or patch is mentioned.
🚨*CVE* 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 t… https://www.cve.org/CVERecord?id=CVE-2026-55615 ----- Traducción: CVE-2026-55615 Lan… http://infoflow.cloud`
Post summary
The post announces CVE‑2026‑55615 in the Langroid framework, noting a pre‑0.65.5 vulnerability in Neo4jChatAgent and directing readers to the CVE record for more details.