CVE-2026-75062 PUBLISHED

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

Assigner: Google
Reserved: 17.08.2026 Published: 26.08.2026 Updated: 26.08.2026

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.

Metrics

CVSS 4.0

CVSS Vector: 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
CVSS Score: 9.2

Exploitability Metrics		Vulnerable System Impact Metrics		Subsequent System Impact Metrics
Attack Vector	Network	Confidentiality	High	Confidentiality	None
Attack Complexity	Low	Integrity	High	Integrity	None
Attack Requirements	Present	Availability	High	Availability	None
Privileges Required	None
User Interaction	None

CVSS 4.0

Product Status

Vendor	Google
Product	langfun
Versions	Default: unaffected affected from 0.0.1 to 0.1.2 (excl.)

References

Problem Types

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

Impacts

CAPEC-242: Code Injection