CVE-2026-45023: AutoGPT: Credit system bypassed via direct block execution in POST /api/blocks/{block_id}/execute
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{blockid}/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.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
AutoGPTto a version that resolves this vulnerability.Fixed in 0.6.59
Event History
Frequently Asked Questions
What is the severity of CVE-2026-45023?
The severity of CVE-2026-45023 is classified as medium with a score of 5.4.
What does CVE-2026-45023 exploit?
CVE-2026-45023 exploits a vulnerability in AutoGPT that allows users to bypass the credit system via direct block execution.
How do I fix CVE-2026-45023?
To fix CVE-2026-45023, update AutoGPT to version 0.6.59 or later, which addresses the credit consumption issue.
What is the impact of CVE-2026-45023?
The impact of CVE-2026-45023 includes unauthorized execution of blocks without deducting credits from the user's balance.
Which software is affected by CVE-2026-45023?
CVE-2026-45023 affects the AutoGPT software prior to version 0.6.59.