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.
Metrics
Affected Vendors & Products
No data.
No data.
No data.
No data.
Advisories
| Source | ID | Title |
|---|---|---|
 Github GHSA |
GHSA-wj6g-v78p-6fx3 | PraisonAI has an origin validation bypass in MCP HTTP Stream transport that allows browser-mediated unauthenticated tool execution on local MCP server |
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Tue, 25 Aug 2026 14:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | 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. | |
| Title | PraisonAI: Origin validation bypass in MCP HTTP Stream transport allows browser-mediated unauthenticated tool execution on local MCP server | |
| Weaknesses | CWE-306 CWE-346 |
|
| References |
| |
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
MITRE
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-08-25T14:26:30.692Z
Reserved: 2026-06-16T23:01:04.073Z
Link: CVE-2026-55529
Vulnrichment
No data.
NVD
No data.
Redhat
No data.
OpenCVE Enrichment
No data.