---
id: CVE-2026-61536
title: Banks generates meaningful LLM prompts using a simple template language
summary: >-
  Banks generates meaningful LLM prompts using a simple template language. In
  versions prior to 2.4.3, banks parses Tool JSON objects from the rendered body
  of {% completion %} blocks and later resolves their import_path field through
  impo…
severity: high
cvss: 7.5
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H'
cwe:
  - CWE-94
  - CWE-470
published: '2026-07-30'
updated: '2026-07-31'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-61536'
references:
  - url: 'https://github.com/masci/banks/security/advisories/GHSA-64vx-6h2c-rjh7'
    label: security-advisories@github.com
  - url: 'https://github.com/masci/banks/security/advisories/GHSA-64vx-6h2c-rjh7'
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
tags:
  - nvd
epss: 0.003
epssPercentile: 0.22889
ingestedAt: '2026-08-01T22:15:46.227Z'
---

## Overview

Banks generates meaningful LLM prompts using a simple template language. In versions prior to 2.4.3, banks parses Tool JSON objects from the rendered body of {% completion %} blocks and later resolves their import_path field through importlib.import_module(...) + getattr(...) to obtain the callable that handles a tool call. There is no allowlist or sanitization on import_path, so any importable Python attribute (e.g. os.system, subprocess.getoutput) can be selected. When the LLM emits a tool_calls entry whose function.name matches the attacker-supplied tool name, the resolved callable is invoked with kwargs decoded from tool_call.function.arguments, yielding arbitrary code execution in the banks-hosting process. This is distinct from GHSA-gphh-9q3h-jgpp / CVE-2026-44209. That advisory was fixed in 2.4.2 by switching src/banks/env.py from Environment to SandboxedEnvironment. The fix does not touch src/banks/extensions/completion.py, and the unsafe import + getattr chain still executes on 2.4.2. The malicious Tool JSON is plain text in the rendered template body — it requires no Jinja attribute access, so the sandbox is irrelevant. This issue has been fixed in version 2.4.3.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.