# CVE-2026-55532

## Summary

- **CVE ID:** CVE-2026-55532
- **Severity:** HIGH
- **CVSS Score:** 7.6 (CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L)
- **CWE:** CWE-346, CWE-352
- **Published:** Aug 25, 2026
- **Last Modified:** Aug 25, 2026

## Description

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.

## Affected Products

- MervinPraison — PraisonAI (< 4.6.58)

## References

- [CNA](https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pvph-5j39-v8qc)
- [CNA](https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1)
- [CNA](https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.13%
- **EPSS Percentile:** 2.7

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._