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.

Project Subscriptions

No data.

Advisories

No advisories yet.

Fixes

Solution

No solution given by the vendor.


Workaround

No workaround given by the vendor.

History

Thu, 27 Aug 2026 18:00:00 +0000

Type Values Removed Values Added
Description 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.
References

Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: mitre

Published:

Updated: 2026-08-27T17:24:43.824Z

Reserved: 2026-04-06T00:00:00.000Z

Link: CVE-2026-37003

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-08-27T20:17:41.107

Modified: 2026-08-27T20:17:41.107

Link: CVE-2026-37003

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses

No weakness.