CVE-2026-55529: PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream _validate_origin method accepts request_origin.startswith(allowed), so…

PriorityP337medium6.9CVSS 3.1

AVNACHPRNUIRSCCHILAN

EPSS

0.12%

2.5th percentile

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream _validate_origin method accepts request_origin.startswith(allowed), so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit tools/call requests to the local MCP server and execute exposed tools. This issue is fixed in version 4.6.58.

Affected

2 ranges

Vendor	Product	Version range	Fixed in
mervinpraison	praisonai	< 4.6.58	4.6.58
mervinpraison	praisonai	>= 0 < 4.6.58	4.6.58

Stop checking back — get the weekly exploitation signal.

Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.