What’s Vulnerable › Vulnerabilities

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

• Severity: critical (CVSS 9.2 v4.0)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.4% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-08-26 · updated 2026-08-31
• Weakness: CWE-95

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

• Google langfun: from 0.0.1 before 0.1.2 — fixed in 0.1.2

How to fix

Upgrade to a fixed version: Google langfun 0.1.2. Check the vendor advisory for mitigations.

References

• https://github.com/google/langfun
• https://github.com/google/langfun/issues/725
• https://github.com/google/langfun/issues/725

Get alerted when CVE-2026-75062 or the next vulnerability affects your stack