CVE-2026-107717
6.5 MEDIUMpublic exploit availablePublished 2026-10-08 · Updated 2026-10-13
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD 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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
Weaknesses
CWE-20
Public exploit & PoC references
- https://github.com/masci/banks/commit/02172b816fb84f6a824cc09a8aca7416f53c12cb
- https://github.com/masci/banks/pull/78
- https://github.com/masci/banks/releases/tag/v2.5.0
- https://github.com/masci/banks/security/advisories/GHSA-hmq2-7hp6-7crh
- https://github.com/masci/banks/security/advisories/GHSA-hmq2-7hp6-7crh
All references
- https://github.com/masci/banks/commit/02172b816fb84f6a824cc09a8aca7416f53c12cb
- https://github.com/masci/banks/pull/78
- https://github.com/masci/banks/releases/tag/v2.5.0
- https://github.com/masci/banks/security/advisories/GHSA-hmq2-7hp6-7crh
- https://github.com/masci/banks/security/advisories/GHSA-hmq2-7hp6-7crh
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- UNSCOREDCVE-2023-5649
- MEDIUMCVE-2025-31980
- MEDIUMCVE-2025-32000
- CRITICALCVE-2025-71383
- HIGHCVE-2026-100113
- HIGHCVE-2026-100117
- HIGHCVE-2026-100119
- HIGHCVE-2026-100120
Related by shared AI tags and CWE weakness class. Browse the full archive.