CVE-2026-37003
CRITICALDescription
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.
Is your site exposed to CVE-2026-37003?
Run a free security scan — no signup, results in seconds.
CVSS v3.1 Score
EPSS — Exploit Prediction
EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.
Weakness Type (CWE)
References
Other References
Frequently Asked Questions
What is CVE-2026-37003? +
How severe is CVE-2026-37003? +
How do I check if I'm vulnerable to CVE-2026-37003? +
Related Vulnerabilities
Grav is a file-based Web platform. Prior to 2.0.7, Grav Blueprint::dynamicData() in system/src/Grav/Common/Data/Blueprint.php sends an editor-controlled Class::method provider and arguments …
Tabby (formerly Terminus) is a highly configurable terminal emulator. Prior to 1.0.217 , Tabby enables several high-risk Electron Fuses, including …
A Local Code Injection Vulnerability exists in the product and version listed above. The vulnerability is due to incorrect default …
Orval generates type-safe JavaScript clients in TypeScript from OpenAPI v3 and Swagger v2 specifications. Prior to 8.21.0, a ${...} expression …
n8n versions before 1.123.69, 2.33.4, and 2.34.1 contain a JavaScript task runner VM sandbox escape. The runner's prototype-freezing routine covers …
Kiota is an OpenAPI based HTTP Client code generator. Prior to 1.32.4, Kiota's PHP generator embedded OpenAPI description, default fields, …