What is the CVSS score of CVE-2026-45023?

CVE-2026-45023 has a CVSS 3.1 base score of 5.4 (Medium). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:L. EPSS exploitation probability: 0.1%.

Is there a patch available for CVE-2026-45023?

Yes, a patch is available for CVE-2026-45023. Update the affected software to the latest version immediately.

AutoGPT CVE-2026-45023

EUVD-2026-33072 MEDIUM

Allocation of Resources Without Limits or Throttling (CWE-770)

2026-05-28 security-advisories@github.com

Denial Of Service

5.4

CVSS 3.1 · Vendor: github

Severity by source

Vendor (github) PRIMARY

5.4 MEDIUM

AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:L

Primary rating from Vendor (github) · only source for this CVE.

CVSS VectorVendor: github

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Unchanged

Confidentiality

None

Integrity

Low

Availability

Low

Lifecycle Timeline

Patch available

May 28, 2026 - 23:02 EUVD

Analysis Generated

May 28, 2026 - 22:30 vuln.today

DescriptionCVE.org

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{block_id}/execute endpoint executes blocks without consuming any credits, regardless of the user's balance. The credit check that exists in the graph execution path (manager.py) is never reached when blocks are called directly via the external API, allowing unlimited free execution of all blocks. This vulnerability is fixed in 0.6.59.

AnalysisAI

Unauthorized credit bypass in AutoGPT allows authenticated users to execute blocks without consuming credits, leading to potential resource exhaustion and loss of availability. A proof-of-concept exploit exists, though no active exploitation has been reported (not in CISA KEV). The vulnerability is fixed in version 0.6.59.