# CVE-2026-37008: CrewAI CodeInterpreterTool sandbox escape via Python object introspection

Source: https://junglewise.ai/threats/cve-2026-37008-crewai-codeinterpretertool-sandbox-escape-via-python-object  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-09-13. Updated: 2026-09-26  
License: CC BY 4.0 with a link back

CVE-2026-37008 · Severity: high · CVSS 8.1 · Published 2026-09-13

CrewAI's CodeInterpreterTool is a component that safely executes Python code within an isolated sandbox environment. The vulnerability allows attackers to escape this sandbox by exploiting Python's object introspection capabilities (such as ctypes.CDLL) to bypass import-time module blocklists and access arbitrary functions and system libraries. This enables remote code execution on the host system when the tool is used to process untrusted code.

## Quick answers

**Is CVE-2026-37008 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-37008 being exploited in the wild.

**How severe is CVE-2026-37008?** High severity, with a CVSS score of 8.1, published 13 September 2026.

**Which products and versions are affected?** CrewAI CrewAI before fb2323b.

**Is there a fix for CVE-2026-37008?** A patch was published on 2026-03-15: Fix committed in commit fb2323b Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-37008 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-37008?** Check whether anything you run is named in the advisory. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The vulnerability is a sandbox escape in CrewAI's restricted Python sandbox that relied on blocking imports at the module level. However, this approach is ineffective because Python's complete object graph remains accessible at runtime, independent of import statements. An attacker can call ctypes.CDLL(None) or similar methods to load the C library and execute arbitrary native code without triggering any import-based restrictions. The sandbox fallback was used when Docker was unavailable; the fix removes this insecure fallback and requires Docker for safe execution, failing closed with RuntimeError otherwise. Unsafe execution can still be enabled via unsafe_mode=True flag with explicit user acknowledgment of the security risks.

## Affected products

- CrewAI CrewAI before fb2323b

## Timeline

- 2026-09-13: disclosed: CVE-2026-37008 published
- 2026-03-15: patched: Fix committed in commit fb2323b

## References

- [https://docs.python.org/3/library/ctypes.html](https://docs.python.org/3/library/ctypes.html)
- [https://github.com/crewAIInc/crewAI/commit/fb2323b3deb3ec62b3965526857e77a2264e4cd0](https://github.com/crewAIInc/crewAI/commit/fb2323b3deb3ec62b3965526857e77a2264e4cd0)