Vulnerability · Published Aug 26, 2026 · Assigned by Google

CVE-2026-75062Eval Injection in google/langfun via default lf.query protocol

Critical 9.2

In plain English

A critical-severity security flaw in langfun from Google. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 29% of all known vulnerabilities).

Severity (CVSS 4.0)9.2Critical

Exploit odds (30 days)0.4%top 71.2% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
Google	langfun	0.0.1 – before 0.1.2

Weakness: CWE-95, CWE-1188 · Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

References

https://github.com/google/langfun product
https://github.com/google/langfun/issues/725 issue-tracking