Eval Injection in google/langfun via default lf.query protocol (CVE-2026-75062) | HOL Guard CVE

Unknown severity · Source severity not reportedCVE-2026-75062

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

Answer in brief

CVE-2026-75062 records a Unknown severity vulnerability in Eval Injection in google/langfun via default lf.query protocol. The current sources do not mark it as known exploited. The current feed maps Google/langfun (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Aug 26, 2026Updated Aug 26, 2026Source checked Aug 26, 2026First seen by HOL Aug 26, 2026Material review Aug 26, 2026

Upstream Advisory

Key facts

Risk: Unknown severitySource severity not reported
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Available

Why this deserves its current priority

A CVSS score is not reported in the current record. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps Google/langfun (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
Google/langfungeneric	>=0.0.1 <0.1.2	0.1.2

Recommended response

Check inventory. Check lockfiles and deployed manifests for Google/langfun.
Review the reported fix. Update Google/langfun to 0.1.2 if you use the affected versions. Test the change in a non-production environment first.

Evidence timeline and material changes

Published upstream
Aug 26, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Aug 26, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Aug 26, 2026

Sources and claim methodology

Upstream source 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.

Quoted source text, attributed separately from HOL analysis.