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.
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| langfun Product | >= 0.0.1, < 0.1.2 | 0.1.2 |
Details and references
More Google advisories
All Google| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Aug 25 | Improper control of a resource through its lifetime in Workers in Google Chrome... | Low3.1 | 152.0.7977.65 |
| Aug 25 | Google Chrome: use after free | Critical9.6 | 152.0.7977.65 |
| Aug 25 | Google Chrome: information disclosure | Medium6.5 | 152.0.7977.65 |
| Aug 25 | Google Chrome: integer overflow | High8.3 | 152.0.7977.65 |
| Aug 25 | Google Chrome: information disclosure | Medium6.5 | 152.0.7977.65 |
| Aug 25 | Google Chrome: use after free | Critical9.6 | 152.0.7977.65 |