CVE-2026-72922 AutoGPT: Webhook provider path confusion bypasses generic webhook secret verification
Attackers can bypass webhook secret verification to execute arbitrary AI agent workflows as the owner, requiring an upgrade to AutoGPT.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-72922?
CVE-2026-72922 is a high-severity authentication bypass vulnerability in Significant-Gravitas AutoGPT, published on 11 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.70, AutoGPT's autogpt_platform/backend/backend/api/features/integrations/router.py webhook_ingress_generic route selected get_webhook_manager(provider) from the untrusted provider URL segment without verifying webhook.provider, allowing a request to /compass/webhooks/{webhook_id}/ingress to use CompassWebhookManager's inherited no-op BaseWebhooksManager.verify_signature instead of GenericWebhooksManager.verify_signature, bypass X-Webhook-Secret for a configured secret_token, and execute a generic webhook graph as its owner. This issue is fixed in version 0.6.70.
Weakness: CWE-287
Which versions are affected by CVE-2026-72922?
How do I fix CVE-2026-72922?
No fix has been published for CVE-2026-72922 yet. Limit exposure of the affected software until one is available.
Upgrade, and rotate credentials and sessions that may have been exposed. More about Authentication bypass.
Is CVE-2026-72922 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-72922 exists.
Sources
Also known as GHSA-349p-3c3r-8mjr.