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.
Metrics
Affected Vendors & Products
| Vendors | Products |
|---|---|
| Masci |
|
No data.
No data.
OpenCVE Enrichment is a feature of OpenCVE that uses AI to automatically link vendors and products to CVEs. Learn more on GitHub.
| Vendors | Products |
|---|---|
| Masci |
|
References
History
Thu, 30 Jul 2026 18:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Masci
Masci banks |
|
| Vendors & Products |
Masci
Masci banks |
Thu, 30 Jul 2026 17:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | 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. | |
| Title | Banks: Unsafe importlib.import_module of attacker-controlled Tool.import_path in CompletionExtension allows RCE | |
| Weaknesses | CWE-470 CWE-94 |
|
| References |
| |
| Metrics |
cvssV3_1
|
MITRE
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-07-30T16:50:01.730Z
Reserved: 2026-07-10T16:27:03.093Z
Link: CVE-2026-61536
Vulnrichment
No data.
NVD
No data.
Redhat
No data.
OpenCVE Enrichment
Updated: 2026-07-30T18:30:04Z