Eval Injection in google/langfun via default lf.query protocol
cve-program · CVE-2026-75062
PublishedImproper 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.
Read the publisher's advisoryAffected versions, risk and source history
Related advisories and sources
Publishers link these advisories through the identifiers shown below. A shared identifier or date alone does not tell you whether your software is affected or whether the advisories describe the same cause.
CVE-2026-75062 · CVE overview and exploitation status
cve-program · CVE-2026-75062
Related changes
Linked by CVE identifierNo related changes are available here.