CVE-2026-55615
Prompt-injection in Langroid Neo4j agent allows Cypher injection, data theft/destruction and potential RCE.
Is CVE-2026-55615 being exploited?
Not confirmed. CVE-2026-55615 does not appear in CISA's Known Exploited Vulnerabilities catalog, which records only exploitation that has been observed and reported publicly. That is evidence of absence of a report, not evidence the flaw is unattacked. EPSS currently estimates a 0.46% probability of exploitation in the next 30 days.
How severe is CVE-2026-55615?
CVE-2026-55615 is rated Critical with a CVSS score of 9.2. Severity describes how bad exploitation would be, not how likely it is: pair it with exploitation evidence before deciding what to patch first.
Is there a patch for CVE-2026-55615?
Yes. A fix has been recorded for CVE-2026-55615. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-55615 affect?
CVE-2026-55615 affects Langroid Neo4jChatAgent (<0.65.5), Langroid <0.65.5, Neo4j servers (APOC or dbms.security enabled). Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-55615?
Upgrade Langroid to >=0.65.5, block untrusted prompts, restrict/disable APOC and dbms.security procedures
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Crafted prompts can inject Cypher to read/modify/delete all graph data; with APOC/dbms.security enabled can execute OS commands and access filesystem.
Immediate action required
- affected< 0.65.5
As published in the CVE Program record. A version outside these ranges is not a statement that it is unaffected — vendors sometimes understate a range, and distribution-backported builds carry upstream numbers that do not reflect what was patched into them.