Skip to content

[new-cve] CVE-2026-37003 — Agno up to and including 2.5.8 is vulnerable to Remote Code Execution (RCE) via  #60

Description

@github-actions

New CVE — AI/LLM Related

CVE ID: CVE-2026-37003
Published: 2026-08-27T20:17:41.107
CVSS Score: N/A

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.

Suggested OWASP Mapping

LLM01

Suggested Action

Review this CVE against the OWASP GenAI Crosswalk entries. Update data/incidents.json or relevant mapping files if this CVE represents a real-world exploitation of a mapped threat.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions