CVE-2026-45023
MEDIUMAutoGP: Credit system bypassed via direct block execution in POST /api/blocks/{block_id}/execute
Title source: cnaDescription
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.
References (1)
Core 1
Core References
X_Refsource_Confirm x_refsource_confirm
https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-8pjg-mfqm-vrhr
Scores
CVSS v3
5.4
EPSS
0.0022
EPSS Percentile
12.6%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:L
CISA SSVC
Vulnrichment
Exploitation
poc
Automatable
no
Technical Impact
partial
Details
CWE
CWE-770
CWE-841
Status
published
Products (1)
Significant-Gravitas/AutoGPT
< 0.6.59
Published
May 28, 2026
Tracked Since
May 29, 2026