| Source | ID | Title |
|---|---|---|
Github GHSA |
GHSA-hmq2-7hp6-7crh | Banks: User-controlled prompt input can be parsed as privileged chat messages |
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
Wed, 14 Oct 2026 00:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Weaknesses | CWE-501 | |
| References |
| |
| Metrics |
threat_severity
|
threat_severity
|
Tue, 13 Oct 2026 17:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
Thu, 08 Oct 2026 22:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Masci
Masci banks |
|
| Vendors & Products |
Masci
Masci banks |
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.
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-10-13T16:16:13.460Z
Reserved: 2026-10-08T17:21:52.975Z
Link: CVE-2026-107717
Updated: 2026-10-13T16:16:08.625Z
Status : Deferred
Published: 2026-10-08T22:17:27.560
Modified: 2026-10-13T17:17:16.860
Link: CVE-2026-107717
OpenCVE Enrichment
Updated: 2026-10-17T09:15:06Z
Github GHSA