Aller au contenu
en Se connecter
6.5 Moyenne

CVE-2026-107717 Banks generates meaningful LLM prompts using a simple template language

Description

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chat_messages() attempts to parse every line of rendered template output as ChatMessage JSON. When an application renders untrusted data and passes the returned ChatMessage objects to an LLM provider, attacker-controlled JSON can cross the prompt boundary and become a system, assistant, or tool message because ChatMessage.role accepts arbitrary strings. This can override application instructions, alter the intended prompt structure, or confuse downstream tool and message handling. This issue is fixed in version 2.5.0.

Produits et versions touchés

Produit Versions touchées Corrigé en
banks 2.5 premières → < 2.5.0 2.5.0

Références

Chronologie

  1. Publiée
  2. Dernière modification

Autres CVE de banks

Les 6 CVE de banks →
CVE-2026-107716 Banks generates meaningful LLM prompts using a simple template language 7.3 Élevée CVE-2026-71492 Banks generates meaningful LLM prompts using a simple template language 6.0 Moyenne CVE-2026-61536 Banks generates meaningful LLM prompts using a simple template language 7.5 Élevée CVE-2026-62663 Banks generates meaningful LLM prompts using a simple template language 7.5 Élevée
Suivre cette CVE