CRITICAL 9.2 NVD
CVE-2026-75062
Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') in the default lf.query Python protocol in Google langfun versions prior
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.
References
- https://github.com/google/langfun
- https://github.com/google/langfun/issues/725
- https://github.com/google/langfun/issues/725
This critical severity vulnerability with a CVSS score of 9.2 was published on 2026-08-26 via NVD.
Risk Timeline
CVE Disclosed2026-08-26 · -1 days ago
Remediation Resources
vulnfeed aggregates 11364 vulnerabilities from NVD, CISA KEV,
Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.