CVE-2026-57125

Critical

Description

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve field can mark execute_command as YAML-approved before @require_approval checks critical tools. This chain allows a remote caller to cause a configured language model agent to invoke arbitrary operating-system commands without credentials or operator interaction. This vulnerability is fixed in praisonai 4.6.59 and praisonaiagents 1.6.59 as fixed versions.

SeverityCritical

CVSS9.8

Exploit probability—

ProductPraisonai

PublishedSep 14, 2026

First seenSep 14, 2026

Weakness typeCWE-306Missing authentication for critical function CWE-863Incorrect authorization

How to fix

Update

praisonai4.6.59 or later
praisonaiagents1.6.59 or later

Affected products

Product	Affected versions	Fixed in
praisonaiPyPI	v < 4.6.59	4.6.59
praisonaiagentsPyPI	v < 1.6.59	1.6.59

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.