Skip to content
GoogleCVE-2026-75062

Google langfun: insecure default

Critical9.2CVE-2026-75062 · Published Aug 26, 2026 · updated Aug 31, 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.

Google advisory

Affected versions

PackageAffectedFixed in
langfun
Product
>= 0.0.1, < 0.1.20.1.2
Details and references
CVSS 4.0
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Severity from
the vendor (its own CVE record or advisory)
Weakness
CWE-95, CWE-1188

More Google advisories

All Google
Advisory
Improper control of a resource through its lifetime in Workers in Google Chrome...
Low3.1Aug 25
Google Chrome: use after free
Critical9.6Aug 25
Google Chrome: information disclosure
Medium6.5Aug 25
Google Chrome: integer overflow
High8.3Aug 25
Google Chrome: information disclosure
Medium6.5Aug 25
Google Chrome: use after free
Critical9.6Aug 25

Critical advisories by email

Wednesdays: the week’s critical and high advisories in the AI and data stack, with the fixed versions. Only in weeks that have some.

Double opt-in. Unsubscribe any time.