# CVE-2026-35002: Agno eval injection in model execution component

Source: https://junglewise.ai/threats/cve-2026-35002-agno-eval-injection-in-model-execution-component  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-04-02. Updated: 2026-07-14  
License: CC BY 4.0 with a link back

CVE-2026-35002 · Severity: critical · CVSS 9.8 · Published 2026-04-02

Agno, an AI agent framework, contains a critical security flaw in how it processes model instructions. An attacker can exploit this to run unauthorized Python code on the server or system hosting the AI agent. This could lead to a complete system takeover, theft of sensitive data, or disruption of AI-driven business operations.

Technologies: [Agno](https://junglewise.ai/threats/technologies/agno), [agno (PyPI)](https://junglewise.ai/threats/technologies/pypi-agno). Vendors: [Agno](https://junglewise.ai/threats/vendors/agno), [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-35002 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-35002 being exploited in the wild.

**How severe is CVE-2026-35002?** Critical severity, with a CVSS score of 9.8, published 2 April 2026.

**Which products and versions are affected?** Agno prior to 2.3.24; agno (PyPI) < 2.3.24, ECOSYSTEM:introduced=0,fixed=2.3.24.

**Is there a fix for CVE-2026-35002?** Yes. agno (PyPI): upgrade to 2.3.24 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-35002 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-35002?** Check whether you run Agno or agno (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- agno (PyPI): upgrade to 2.3.24 or later

  ```sh
  pip install "agno>=2.3.24"
  ```


## Technical details

An eval injection vulnerability (CWE-95) exists in Agno's model execution component due to the unsafe use of the Python eval() function. The vulnerability is located in the handling of the field_type parameter within a FunctionCall. A remote, unauthenticated attacker can influence this parameter to execute arbitrary Python code in the context of the application. The issue was addressed in version 2.3.24 by replacing the dynamic eval() call with a secure dictionary-based type mapping.

## Affected products

- Agno Agno prior to 2.3.24

## Identifiers

- CVE-2026-35002
- GHSA-77rh-m34w-rv36
- GHSA-m4w4-3r8h-jw98
- PYSEC-2026-256

## Timeline

- 2026-01-08: patched: Version 2.3.24 released
- 2026-04-02: advisory: Initial disclosure by VulnCheck and NVD

## References

- [https://github.com/agno-agi/agno/commit/cbf675521d4d2281925a051784a3b94172e56416](https://github.com/agno-agi/agno/commit/cbf675521d4d2281925a051784a3b94172e56416)
- [https://github.com/agno-agi/agno/releases/tag/v2.3.24](https://github.com/agno-agi/agno/releases/tag/v2.3.24)
- [https://www.vulncheck.com/advisories/agno-field-type-eval-injection-arbitrary-code-execution](https://www.vulncheck.com/advisories/agno-field-type-eval-injection-arbitrary-code-execution)

## Related threats

- [Agno unsafe reflection in PandasTools](https://junglewise.ai/threats/cve-2026-119050-agno-through-3-1-11-contains-an-unsafe-reflection-vulnerability)
- [Agno prompt injection remote code execution in PythonTools and ShellTools](https://junglewise.ai/threats/cve-2026-37003-agno-prompt-injection-remote-code-execution-in-pythontools-and)
- [Agno SQL injection in ClickHouse vector database backend](https://junglewise.ai/threats/cve-2026-10105-agno-sql-injection-in-clickhouse-vector-database-backend)
- [PYSEC-2026-1077 - Agno session state overwrites between different sessions/users](https://junglewise.ai/threats/cve-2025-64168-agno-session-state-overwrites-between-different-sessions-users)