CVE-2026-56076

What it is

PraisonAI before 1.5.128 contains a cross-origin agent execution vulnerability in the AGUI endpoint that allows remote attackers to trigger arbitrary agent execution. The POST /agui endpoint lacks authentication and hardcodes Access-Control-Allow-Origin: * headers, combined with Starlette's Content-Type-agnostic JSON parsing, enabling attackers to bypass CORS preflight checks via simple requests and exfiltrate sensitive agent responses including tool execution results and environment data.

At a glance

Exploitability

Can be exploited over the network without logging in, but needs a user to act. High risk of data exposure, data tampering.

Exploit odds

0.6% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-06-18 23:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-10-08 16:17 UTC Last updatedMost recent change to the record

Details

Published

2026-06-18 23:16 UTC

Last modified

2026-10-08 16:17 UTC

Exploit probability

0.6% · EPSS, next 30 days

Weakness

CWE-942

Record status

Deferred

Attack profile CVSS 4.0 · 8.6

Attack vector

Network

Complexity

Low

Attack requirements

None

Privileges needed

None

User interaction

Passive

Confidentiality

High

Integrity

High

Availability

None