CVE-2026-72922: CWE-287: Improper Authentication in Significant-Gravitas AutoGPT
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.
AI Analysis
Technical Summary
AutoGPT versions before 0.6.70 contain an authentication bypass vulnerability in the webhook ingress route (/compass/webhooks/{webhook_id}/ingress). The route uses get_webhook_manager(provider) based on an untrusted provider URL segment without verifying webhook.provider. This flaw allows requests to use CompassWebhookManager's inherited no-op BaseWebhooksManager.verify_signature instead of the intended GenericWebhooksManager.verify_signature, bypassing the X-Webhook-Secret validation for a configured secret_token. Consequently, an attacker can execute a generic webhook graph with the privileges of its owner. The issue is resolved in AutoGPT version 0.6.70.
Potential Impact
An attacker can bypass webhook signature verification and authentication controls, allowing unauthorized execution of webhook graphs with owner privileges. This results in a high impact on integrity and a low impact on confidentiality, with no availability impact reported. The CVSS 3.1 score is 8.2 (high severity).
Mitigation Recommendations
Upgrade AutoGPT to version 0.6.70 or later, where this authentication bypass vulnerability is fixed. No other mitigation or workaround is indicated in the available data.
CVE-2026-72922: CWE-287: Improper Authentication in Significant-Gravitas AutoGPT
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.
CVSS v3.1
Score 8.2high
Affected software
Significant-Gravitas
AutoGPT
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
AutoGPT versions before 0.6.70 contain an authentication bypass vulnerability in the webhook ingress route (/compass/webhooks/{webhook_id}/ingress). The route uses get_webhook_manager(provider) based on an untrusted provider URL segment without verifying webhook.provider. This flaw allows requests to use CompassWebhookManager's inherited no-op BaseWebhooksManager.verify_signature instead of the intended GenericWebhooksManager.verify_signature, bypassing the X-Webhook-Secret validation for a configured secret_token. Consequently, an attacker can execute a generic webhook graph with the privileges of its owner. The issue is resolved in AutoGPT version 0.6.70.
Potential Impact
An attacker can bypass webhook signature verification and authentication controls, allowing unauthorized execution of webhook graphs with owner privileges. This results in a high impact on integrity and a low impact on confidentiality, with no availability impact reported. The CVSS 3.1 score is 8.2 (high severity).
Mitigation Recommendations
Upgrade AutoGPT to version 0.6.70 or later, where this authentication bypass vulnerability is fixed. No other mitigation or workaround is indicated in the available data.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-08-10T17:57:26.144Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6a7b3853bf8831d539e79e44
Added to database: 08/11/2026, 14:57:23 UTC
Last enriched: 08/11/2026, 15:11:31 UTC
Last updated: 09/24/2026, 01:47:44 UTC
Views: 65
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.