Google Langfun Eval Injection via lf.query before 0.1.2
CVE-2026-75062 Published on August 26, 2026

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

NVD

Vulnerability Analysis

CVE-2026-75062 is exploitable with network access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. Public availability of a proof of concept (POC) exploit exists for CVE-2026-75062. The potential impact of an exploit of this vulnerability is considered to have no impact on confidentiality and integrity and availability.

Attack Vector:
NETWORK
Attack Complexity:
LOW
Privileges Required:
NONE
User Interaction:
NONE

Weakness Types

What is an Eval Injection Vulnerability?

The software receives input from an upstream component, but it does not neutralize or incorrectly neutralizes code syntax before using the input in a dynamic evaluation call (e.g. "eval"). This may allow an attacker to execute arbitrary code, or at least modify what code can be executed.

CVE-2026-75062 has been classified to as an Eval Injection vulnerability or weakness.

Insecure Default Initialization of Resource

The software initializes or sets a resource with a default that is intended to be changed by the administrator, but the default is not secure.


Affected Versions

Google langfun: