Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · Agno

CVE-2026-35002: Agno is vulnerable to Eval Injection

criticalCVSS 4.0 9.3GHSA-77rh-m34w-rv36

Agno versions prior to 2.3.24 contain an arbitrary code execution vulnerability in the model execution component that allows attackers to execute arbitrary Python code by manipulating the fieldtype parameter passed to eval(). Attackers can influence the fieldtype value in a FunctionCall to achieve remote code execution.

Published Apr 2, 2026 · Updated Apr 4, 2026

Affected packages

agno

Ecosystem
PyPI
Affected
< 2.3.24
Fixed in
2.3.24
Check
pip show agno

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Agno versions prior to 2.3.24 contain an arbitrary code execution vulnerability in the model execution component that allows attackers to execute arbitrary Python code by manipulating the field_type parameter passed to eval(). Attackers can influence the field_type value in a FunctionCall to achieve remote code execution.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More Agno vulnerabilities

All Agno entries