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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-306",
"CWE-346"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/55xxx/CVE-2026-55529.json"
}{
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "4.6.58"
}
],
"source": [
"AFFECTED_FIELD",
"REFERENCES"
]
}