Unauthenticated graph execution via webhook provider confusion
Published Aug 11, 2026 · Updated Aug 11, 2026
Authentication bypass in Significant Gravitas AutoGPT before 0.6.70 allows remote attackers to trigger protected webhook graphs without a secret. The webhook ingress route chooses a verification manager from the untrusted provider path before loading the stored webhook, never checks that the provider values match, and can substitute Compass's inherited no-op verifier for the generic webhook verifier. Exploitation requires knowledge of a protected webhook UUID; a forged request can run the graph as its owner and invoke actions under the owner's connected credentials.
Summary
What happened
Authentication bypass in Significant Gravitas AutoGPT before 0.6.70 allows remote attackers to trigger protected webhook graphs without a secret. The webhook ingress route chooses a verification manager from the untrusted provider path before loading the stored webhook, never checks that the provider values match, and can substitute Compass's inherited no-op verifier for the generic webhook verifier. Exploitation requires knowledge of a protected webhook UUID; a forged request can run the graph as its owner and invoke actions under the owner's connected credentials.
The record
- CVE
- CVE-2026-72922
- Published
- Aug 11, 2026
- Updated
- Aug 11, 2026
- Vendor
- Significant Gravitas
- Product
- AutoGPT
- Classifications
- CWE-287, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 11, 2026CVE publishedPublication date reported by the CVE source.
- Aug 11, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.6.70
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
- Upstream webhook provider-confusion reproductionproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo