CVE-2026-107717
Banks: User-controlled prompt input can be parsed as privileged chat messages
MEDIUM 6.5EPSS 0.3%
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.
- Affected
- masci · banks
- CVSS v3.1 GITHUB
- 6.5 MEDIUM
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N - EPSS
- 0.28% chance of exploitation in the next 30 days, 19th percentile
- Published
- 2026-10-08
- Updated
- 2026-10-13