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
Configurations
No configuration.
History
No history.
Information
Published : 2026-08-27 20:17
Updated : 2026-09-08 19:29
NVD link : CVE-2026-37003
Mitre link : CVE-2026-37003
CVE.ORG link : CVE-2026-37003
JSON object : View
Products Affected
No product.
CWE
CWE-94
Improper Control of Generation of Code ('Code Injection')
