High severity7.6NVD Advisory· Published Aug 25, 2026· Updated Sep 9, 2026
CVE-2026-55532
CVE-2026-55532
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
PraisonAIPyPI | < 4.6.58 | 4.6.58 |
Affected products
1Patches
Vulnerability mechanics
References
4News mentions
0No linked articles in our index yet.