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 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.
Scoring
- Severity
- HIGH
- CVSS base score
- 7.6
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L
- EPSS probability
- 0.13%
- CWE
- CWE-346, CWE-352
- Published
- 2026-08-25
- Last modified
- 2026-08-25
Affected products
- MervinPraison PraisonAI
Weakness type
Related vulnerabilities
- CVE-2026-87563 — Origin validation error in Paint in Google Chrome prior to 153.0.8010.36 allowed a remote attacker...
- CVE-2026-58649 — .NET Information Disclosure Vulnerability
- CVE-2026-69559 — Microsoft Teams for Android Information Disclosure Vulnerability
- CVE-2026-69680 — Windows DNS Spoofing Vulnerability
- CVE-2026-75156 — Apache Airflow FAB provider: FAB Azure AD OAuth: id_token issuer/audience not validated — cross-tenant authentication bypass
- CVE-2026-85152 — undici vulnerable to cross-origin cache poisoning via missing origin isolation in interceptors
- CVE-2026-84482 — WWBN AVideo Cross-Site Request Forgery via get_domain() validation
- CVE-2026-82811 — Toggl OÜ Toggl Track Extension postMessage origin validation