CVE-2026-39890

Description

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags (such as !!js/function and !!js/undefined). This allows an attacker to craft a malicious YAML file that, when parsed, executes arbitrary JavaScript code. An attacker can exploit this vulnerability by uploading a malicious agent definition file via the API endpoint, leading to remote code execution (RCE) on the server. This vulnerability is fixed in 4.5.115.

Weakness classification

• security-advisories@github.com: CWE-502

Primary references

• security-advisories@github.com — Vendor Advisory
• 134c704f-9b21-4f2e-91b3-4a467353bcc0 — Vendor Advisory