CVE-2026-107717
mediumBanks generates meaningful LLM prompts using a simple template language.
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.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N Affected products
Not reported by the source (unknown — not "none").
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
No vendor advisory or patch reference tagged by NVD. Check the references below.
References
- https://github.com/masci/banks/commit/02172b816fb84f6a824cc09a8aca7416f53c12cb security-advisories@github.com
- https://github.com/masci/banks/pull/78 security-advisories@github.com
- https://github.com/masci/banks/releases/tag/v2.5.0 security-advisories@github.com
- https://github.com/masci/banks/security/advisories/GHSA-hmq2-7hp6-7crh security-advisories@github.com
- https://github.com/masci/banks/security/advisories/GHSA-hmq2-7hp6-7crh 134c704f-9b21-4f2e-91b3-4a467353bcc0