CVE-2026-57132

Published: Sep 14, 2026Modified: Sep 16, 2026Deferred

8.2

Vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

Exploitability: 3.9 / Impact: 4.2

Source: security-advisories@github.com (Secondary)

Description

PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAI_CALL_AUTH to disabled makes verify_token accept requests to /api/v1/agents/{id}/invoke without CALL_SERVER_TOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their connected tools or private context to unauthenticated invocation. The vulnerability is fixed in 4.6.62.

Related CWEs

CWE-287

Improper Authentication

When an actor claims to have a given identity, the product does not prove or insufficiently proves that the claim is correct.

References (4)

https://github.com/MervinPraison/PraisonAI/commit/2a855c470077c7d2e2479a575f7ef7f548d51c33

Source: security-advisories@github.com

https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62

Source: security-advisories@github.com

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8ccj-p46r-jwqq

Source: security-advisories@github.com

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8ccj-p46r-jwqq

Source: 134c704f-9b21-4f2e-91b3-4a467353bcc0

Timeline

No history available yet.