RCE in Google Langfun
CVE-2026-75062
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.
Published · last modified .
EPSS exploit prediction
EPSS: 0.004 (26.6th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 27th percentile — 26.6% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.002 · newest: 0.004 · change: +0.001
Affected products
Weakness classification (CWE)
References
- github.com/google/langfun (product)
- github.com/google/langfun/issues/725 (issue-tracking)