CVE-2026-45023Public exploitNetwork attack vector

Authenticated credit bypass via direct block execution

Published May 28, 2026 · Updated May 28, 2026

Business logic bypass in AutoGPT before 0.6.59 allows remote authenticated users to execute API blocks without consuming credits. The external API handler in routes.py invokes obj.execute(data) directly, so the balance guard in executor/manager.py's graph path is never reached. Any authenticated account can run blocks repeatedly without billing or rate-limit enforcement, consuming platform and model resources.

CVSS severity5.4
Medium
EPSS probability0.22%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Business logic bypass in AutoGPT before 0.6.59 allows remote authenticated users to execute API blocks without consuming credits. The external API handler in routes.py invokes obj.execute(data) directly, so the balance guard in executor/manager.py's graph path is never reached. Any authenticated account can run blocks repeatedly without billing or rate-limit enforcement, consuming platform and model resources.

The record

CVE
CVE-2026-45023
Published
May 28, 2026
Updated
May 28, 2026
Vendor
Significant Gravitas
Product
AutoGPT
Classifications
CWE-841, CWE-770, T1496
Attack vector
network
Privileges
authenticated

Timeline

How it unfolded

  1. May 28, 2026CVE publishedPublication date reported by the CVE source.
  2. May 28, 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.

  1. Affected versionversion=< 0.6.59

What conditions does exploitation require?

Attack vectornetwork
Required privilegesauthenticated

What is affected?

Significant Gravitas · AutoGPTversion=< 0.6.59

Published CVSS scores

5.4GitHub, Inc.CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:L

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.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-841Improper Enforcement of Behavioral Workflow
CWE-770Allocation of Resources Without Limits or Throttling
T1496Resource Hijacking

Public exploit references

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