CVE-2026-107717
Banks: User-controlled prompt input can be parsed as privileged chat messages
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.
| CWE | CWE-20 |
| Vendor | masci |
| Product | banks |
| Published | Oct 8, 2026 |
Get instant alerts for masci banks
Be the first to know when new medium vulnerabilities affecting masci banks are published — delivered to Slack, Telegram or Discord.
CVSS v3 Breakdown
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N