HIGH 7.6 NVD

CVE-2026-55532

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attac

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests without preflight and invoke tools/call without an API key, including file writes that persist agent instructions. This issue is fixed in version 4.6.58.

References

Published: 2026-08-25 · Source: NVD · Feed updated: 2026-08-25
This high severity vulnerability with a CVSS score of 7.6 was published on 2026-08-25 via NVD.
vulnfeed aggregates 11954 vulnerabilities from NVD, CISA KEV, Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.