UTC
Critical

Agno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`

CVE-2026-35002 · GHSA-m4w4-3r8h-jw98 · published 2026-10-27

Severity
Critical
CVSS score
9.8
Chance of exploitation (EPSS)
0.86%
Fixed in
2.3.24
  • Exploitation No known exploitation
  • Automatable Yes
  • Technical impact Total
  • CISA SSVC
What it is

Agno versions prior to 2.3.24 contain an arbitrary code execution vulnerability in the model execution component. The field_type parameter on a FunctionCall input field was passed to Python's built-in eval(), allowing an attacker who could influence that value to execute arbitrary Python code in the Agno process. This is a code injection flaw (CWE-95) with full impact to confidentiality, integrity, and availability. CVSS 3.1 score: 9.3 (Critical). Any deployment that exposes Agno to user-influenced FunctionCall inputs (for example via an API, web UI, or untrusted tool/model output) is affected.

What to do

Upgrade agno to 2.3.24 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Fixed in Agno 2.3.24. The unsafe eval() call was replaced with a fixed typemapping dictionary lookup, and fieldtype is now validated as either a known string key or an already-resolved type object before use. See commit cbf67552 (PR #5912). All users should upgrade to 2.3.24 or later. The current release line (2.6.x) includes the fix.

If you cannot upgrade yet

There is no safe workaround. Users who cannot upgrade should ensure no untrusted input can reach the field_type parameter of FunctionCall input fields, but upgrading is strongly preferred.

Affected
PackageRegistryAffectedFixed in
agnoPyPI< 2.3.242.3.24

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].