Critical severityNVD Advisory· Published Aug 26, 2026· Updated Aug 26, 2026
CVE-2026-75062
CVE-2026-75062
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
1Patches
Vulnerability mechanics
References
1News mentions
0No linked articles in our index yet.