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…
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.23%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 4.0
- 9.2 CRITICALCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
- EPSS
- 0.23% probability · 14th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-95, CWE-1188
- Source
- cve-coordination@google.com
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.