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.
Metrics
Affected Vendors & Products
No data.
No data.
No data.
No data.
Advisories
No advisories yet.
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Thu, 08 Oct 2026 21:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | Banks: User-controlled prompt input can be parsed as privileged chat messages | |
| Weaknesses | CWE-20 | |
| References |
| |
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
MITRE
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-10-08T21:38:07.447Z
Reserved: 2026-10-08T17:21:52.975Z
Link: CVE-2026-107717
Vulnrichment
No data.
NVD
No data.
Redhat
No data.
OpenCVE Enrichment
No data.
Weaknesses