7.6highHigh
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.
What the metrics mean
- It is reachable over a network, without needing local access.
- For an attacker who can reach it, no special conditions are needed to exploit it.
- To exploit it, no account is needed.
- Beyond that, someone has to be persuaded to take an action first.
Scoring
- CVSS
- 7.6 (v3.1)
- Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L- Weakness
- CWE-346
- Assigned by
- security-advisories@github.com
Dates
- Published
- 2026-08-25
- Last modified
- 2026-09-09
- Sources
- NVD