Skip to content

CVE-2026-22038 AutoGPT's API Keys and Secrets Logged in Plaintext in Stagehand Integration Blocks

HighCVSS 8.1 EPSS 0.49%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
No known exploitation · automatable: no · technical impact: partial

Description

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.46, the AutoGPT platform's Stagehand integration blocks log API keys and authentication secrets in plaintext using logger.info() statements. This occurs in three separate block implementations (StagehandObserveBlock, StagehandActBlock, and StagehandExtractBlock) where the code explicitly calls api_key.get_secret_value() and logs the result. This issue has been patched in autogpt-platform-beta-v0.6.46.

Upgrade path

2 packages: 1 fixed.

PackageAffectedFixed inStatus
agpt autogpt platform < 0.6.46 0.6.46 Fixed
Significant-Gravitas AutoGPT = < autogpt-platform-beta-v0.6.46 No fix listed Versions listed

Affected products

ProductAffected versionsFixed in
Significant-Gravitas AutoGPT = < autogpt-platform-beta-v0.6.46 No fix listed
agpt autogpt platform < 0.6.46 0.6.46

References