Vulnerability · Published Oct 8, 2026 · Assigned by GitHub_M

CVE-2026-107717Banks: User-controlled prompt input can be parsed as privileged chat messages

Medium 6.5

In plain English

A medium-severity improper input validation in banks from masci. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 27% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.5Medium

Exploit odds (30 days)0.3%top 73.0% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	banks	2.5.0	GHSA-hmq2-7hp6-7crh
PyPI	banks	2.5.0	PYSEC-2026-4202

Affected products (as reported)

Vendor	Product	Versions
masci	banks	< 2.5.0

Weakness: CWE-20 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N

References

https://github.com/masci/banks/security/advisories/GHSA-hmq2-7hp6-7crh x_refsource_CONFIRM
https://github.com/masci/banks/pull/78 x_refsource_MISC
https://github.com/masci/banks/commit/02172b816fb84f6a824cc09a8aca7416f53c12cb x_refsource_MISC
https://github.com/masci/banks/releases/tag/v2.5.0 x_refsource_MISC