Naar de inhoud
CodeAuditAgent

CVE-2026-41713

A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. Applications using the affected advisor with user-controlled input may be susceptible to manipulation of model behavior across conversation turns.

Zwakheid

A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. Applications using the affected advisor with user-controlled input may be susceptible to manipulation of model behavior across conversation turns.

Getroffen producten

  • vmware spring_ai

Bronnen

Vind de bug voordat een aanvaller dat doet.

Log in met GitHub en start je eerste audit binnen een minuut. Voor het gratis abonnement is geen creditcard nodig.