CVE-2026-75062

Eval Injection in google/langfun via default lf.query protocol

State: Published
Severity: 9.2 Critical
Published: Aug 26, 2026
Updated: Aug 27, 2026
Reserved: Aug 17, 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.

Scores

CVSS	Score	Vector	Source
4.0	9.2 Critical	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	Google

Weaknesses

CWE-95 Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
CWE-1188 Insecure Default Initialization of Resource

Affected Products

Product	Versions
langfunGoogle	0.0.1 to before 0.1.2Affected

References

https://github.com/google/langfunproduct
https://github.com/google/langfun/issues/725issue-tracking

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.