CVE-2026-56823
MediumCVSS 5.4Exploitation Probability (EPSS)
Low risk5th percentile — higher than 5% of all known CVEs
Summary
A vulnerability in AutoGPT allows an authenticated user to access the `POST /api/integrations/webhooks/{webhook_id}/ping` endpoint without verifying that the webhook belongs to them. An attacker can confirm webhook existence, leak the OAuth provider type, and in some cases trigger a ping delivery on behalf of another user.
Risk Assessment
The risk involves unauthorized confirmation of webhook existence and leakage of OAuth provider type, which could lead to further social engineering attacks or privacy breaches.
Recommendation
Immediately update AutoGPT to a version that fixes this vulnerability and implement ownership verification mechanisms before performing ping operations.
Original NVD description (English source)
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to , the `POST /api/integrations/webhooks/{webhook_id}/ping` endpoint fetches the target webhook by primary key alone without verifying that the webhook belongs to the authenticated user. Any authenticated user can supply an arbitrary webhook_id to confirm webhook existence, leak the webhook's OAuth provider type, and in some cases trigger a ping delivery on behalf of another user. This vulnerability is fixed in .