VULNERABILITY INTELLIGENCE
CVE-2026-75062
EPSS probability0.35%
CISA KEVNot currently listed
Published2026-08-26
Last modified2026-08-31
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.
Weakness classification
- cve-coordination@google.com: CWE-95