CVE-2026-75062 Eval Injection in google/langfun via default lf.query protocol
Remote attackers can execute arbitrary Python code via crafted prompts in the default query protocol of the Google langfun library.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-75062?
CVE-2026-75062 is a critical code injection vulnerability in Google langfun, published on 26 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Which versions are affected by CVE-2026-75062?
How do I fix CVE-2026-75062?
No fix has been published for CVE-2026-75062 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-75062 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-75062 exists.
Sources
Also known as GHSA-8x83-862f-c85r.