---
id: CVE-2026-37003
title: >-
  Agno up to and including 2.5.8 is vulnerable to Remote Code Execution (RCE)
  via prompt injection
summary: >-
  Agno up to and including 2.5.8 is vulnerable to Remote Code Execution (RCE)
  via prompt injection. The PythonTools and ShellTools components pass
  unsanitized, LLM-generated arguments directly to execution sinks including
  exec(), runpy.run…
severity: critical
cvss: 9.8
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'
cwe:
  - CWE-94
published: '2026-08-27'
updated: '2026-09-08'
sourceUpdated: '2026-09-08T19:29:09.680'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-37003'
references:
  - url: 'http://agno.com'
    label: cve@mitre.org
  - url: 'https://yerangamage.com/cves/detail/?slug=agno-rce-tools'
    label: cve@mitre.org
tags:
  - nvd
epss: 0.01321
epssPercentile: 0.69641
ingestedAt: '2026-09-08T20:10:03.158Z'
---

## Overview

Agno up to and including 2.5.8 is vulnerable to Remote Code Execution (RCE) via prompt injection. The PythonTools and ShellTools components pass unsanitized, LLM-generated arguments directly to execution sinks including exec(), runpy.run_path(), and subprocess.run(). An unauthenticated attacker can exploit this by embedding malicious instructions in content processed by the agent (such as web pages or documents), allowing for arbitrary code and OS command execution on the host server.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.