CVE-2026-72922
Received Received - Intake

Webhook Signature Bypass in AutoGPT Platform

Publication date: 2026-08-11

Last updated on: 2026-08-11

Assigner: GitHub, Inc.

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 Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-08-11
Last Modified
2026-08-11
Generated
2026-08-11
AI Q&A
2026-08-11
EPSS Evaluated
N/A
NVD
CVE-2026-72922
EUVD
EUVD-2026-56177

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
significant_gravitas autogpt to 0.6.70 (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-287 When an actor claims to have a given identity, the product does not prove or insufficiently proves that the claim is correct.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability in AutoGPT (CVE-2026-72922) allows an attacker to bypass webhook signature verification by manipulating the provider name in the URL path. The system selects a webhook manager based on the provider in the URL without checking if it matches the stored webhook's provider, enabling unauthorized execution of webhook graphs.

Detection Guidance

Check AutoGPT version with: pip show autogpt or git log --oneline | grep autogpt-platform-beta-v0.6.70. Inspect webhook logs for mismatched provider paths or unauthorized ingress attempts to /compass/webhooks/{id}/ingress.

Impact Analysis

An attacker could exploit this to execute unauthorized actions using your AutoGPT instance's credentials. This could lead to data breaches, unauthorized workflow execution, or integration with malicious services without proper authentication.

Compliance Impact

This vulnerability could violate compliance requirements by allowing unauthorized access to sensitive data or systems. GDPR requires data protection and access controls, while HIPAA mandates strict authentication for health data. Exploitation could lead to unauthorized data exposure or processing, violating these standards.

Mitigation Strategies

Upgrade AutoGPT to version 0.6.70 or later immediately. Review webhook configurations to ensure provider paths match stored webhook providers. Monitor for unauthorized webhook execution attempts.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-72922. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart