CVE-2026-72922
AutoGPT: Webhook provider path confusion bypasses generic webhook secret verification
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- Low
- Integrity
- High
- Availability
- None
Exploit likelihood
What each source reports
CVE List Score used
8.2
AutoGPT: Webhook provider path confusion bypasses generic webhook secret verification
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.
- Record
CVE-2026-72922- CVSS 3.1
- 8.2 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N - Weakness
- CWE-287
- Updated
- 2026-11-02
EUVDEUVD-2026-56177
8.2
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.
- Record
EUVD-2026-56177- CVSS 3.1
- 8.2 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N - Updated
- 2026-11-02
NVD
8.2
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.
- Record
CVE-2026-72922- CVSS 3.1
- 8.2 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N - Weakness
- CWE-287
- Updated
- 2026-11-02
OSV
8.2
AutoGPT: Webhook provider path confusion bypasses generic webhook secret verification
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.
- Record
CVE-2026-72922- CVSS 3.1
- 8.2 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N - Weakness
- CWE-287
- Updated
- 2026-11-02
Affected products
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-72922 is a high vulnerability (CVSS 8.2) in Significant-gravitas Autogpt, published August 11, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.48%, the 41st percentile. No source names a fixed version.
References
github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-349p-3c3r-8mjr
github.com/Significant-Gravitas/AutoGPT/pull/13559
github.com/Significant-Gravitas/AutoGPT/commit/646dd5b8cfad1206e92ec7bcc3b8312657e2a92e
github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.70
github.com/CVEProject/cvelistV5/tree/main/cves/2026/72xxx/CVE-2026-72922.json
nvd.nist.gov/vuln/detail/CVE-2026-72922