Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') Affecting banks package, versions [,2.5.0)
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-BANKS-20849383
- published13 Oct 2026
- disclosed8 Oct 2026
- creditMuhammedali Aliyev
Introduced: 8 Oct 2026
NewCVE-2026-107717 (opens in a new tab)How to fix?
Upgrade banks to version 2.5.0 or higher.
Overview
banks is an A prompt programming language
Affected versions of this package are vulnerable to Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') via Prompt.chat_messages(), which parsed every line of a rendered template as a possible ChatMessage without distinguishing between trusted template structure and untrusted template data. An attacker who controls data rendered into a prompt can inject JSON that is interpreted as a privileged system, assistant, or tool message. The same parsing path also affected CompletionExtension._body_to_messages(), where data could inject tool definitions, and chat_message_from_text(), where data could inject content blocks such as remote image URLs through the no-chat-block fallback.