PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-72922 Significant-Gravitas CVE debrief

CVE-2026-72922 AutoGPT Webhook Signature Bypass. AutoGPT, a workflow automation platform, contains a high-severity vulnerability in its webhook ingress route. This vulnerability, identified as CVE-2026-72922, allows for signature bypass and execution of a generic webhook graph as its owner. The issue arises from the incorrect selection of the webhook manager based on an untrusted provider URL segment without verifying the webhook provider. This bypasses the X-Webhook-Secret for a configured secret_token. Defenders responsible for AutoGPT deployments should assess exposure and verify webhook configurations. Security teams and developers using AutoGPT should prioritize updating to a

Vendor
Significant-Gravitas
Product
AutoGPT
CVSS
HIGH 8.2
CISA KEV
Not listed in stored evidence
Original CVE published
2026-08-11
Original CVE updated
2026-09-09
Advisory published
2026-08-11
Advisory updated
2026-09-09

Who should care

Defenders responsible for AutoGPT deployments should assess exposure and verify webhook configurations. Security teams and developers using AutoGPT should prioritize updating to version 0.6.70 or later.

Why it matters

CVE-2026-72922 is a high-severity vulnerability in AutoGPT's webhook ingress route, allowing for signature bypass and execution of a generic webhook graph. Defenders should prioritize updating to version 0.6.70 or later and verify webhook configurations.

  • Bypassing webhook signature verification can lead to unauthorized execution of webhook graphs.
  • Execution of a generic webhook graph as its owner can result in unintended actions.
  • Verification of webhook configurations and secret tokens is necessary to prevent exploitation.
  • Updating to version 0.6.70 or later is required to fix the vulnerability.

Technical summary

The AutoGPT platform, prior to version 0.6.70, contains a vulnerability in its webhook ingress route. The route incorrectly selects the webhook manager based on the untrusted provider URL segment without verifying the webhook provider. This allows an attacker to bypass the X-Webhook-Secret for a configured secret_token and execute a generic webhook graph as its owner. The vulnerability is a result of insufficient verification of the webhook provider, leading to a bypass of the signature verification process. This issue is fixed in version 0.6.70, where the verification process has been corrected to prevent such bypasses. Affected AutoGPT deployments should be updated to this version or later to mitigate the

Defensive priority

High

Recommended defensive actions

  • Review and update AutoGPT to version 0.6.70 or later
  • Verify webhook configurations and secret tokens
  • Monitor for suspicious webhook activity
  • Confirm whether affected AutoGPT deployments exist in managed environments and assign an owner for follow-up.
  • Review the supplied official advisory or CVE record to validate affected scope, severity, and vendor guidance.
  • Plan vendor-supported updates or mitigations through normal change control where exposure is confirmed.
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review.

Evidence notes

The CVE record and NVD entry provide details on the vulnerability in AutoGPT's webhook ingress route. The issue allows for bypassing the X-Webhook-Secret for a configured secret_token and executing a generic webhook graph as its owner. This is fixed in version 0.6.70.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-72922 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-72922

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-72922 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-72922

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.