# CVE-2026-75062

## Summary

- **CVE ID:** CVE-2026-75062
- **Severity:** CRITICAL
- **CVSS Score:** 9.2 (CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N)
- **CWE:** CWE-95, CWE-1188
- **Published:** Aug 26, 2026
- **Last Modified:** Aug 27, 2026

## Description

Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') in the default lf.query Python protocol in Google langfun versions prior to 0.1.2 allows remote unauthenticated attackers to execute arbitrary Python code in the context of the host application via crafted prompt inputs that cause the model to generate executable Python expressions evaluated without a sandbox.

## Affected Products

- Google — langfun (0.0.1)

## References

- [CNA](https://github.com/google/langfun)
- [CNA](https://github.com/google/langfun/issues/725)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.23%
- **EPSS Percentile:** 13.9

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._