CVE-2026-22038 Details
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.
A vulnerability exists in the AutoGPT platform's Stagehand integration, prior to version 0.6.46, where API keys and authentication secrets are logged in plaintext. This issue arises in three block implementations—StagehandObserveBlock, StagehandActBlock, and StagehandExtractBlock—where the code explicitly retrieves secret values using 'get_secret_value()' and logs them using 'logger.info()'. As a result, sensitive credentials for various API providers, including Stagehand/Browserbase, OpenAI, Anthropic, and Groq, are exposed in application logs. The vulnerability can be exploited by accessing these logs, particularly if they are aggregated or stored in a way that allows for searching and retrieval of the exposed secrets.
The recommended fix is to remove the logging of secret values entirely or redact them before logging. If detailed logging is necessary for debugging, use 'logger.debug()' instead of 'logger.info()', and ensure that debug logging is disabled in production.
Metrics
CVSS 4.0 Severity and Vector Strings:
No CVSS 4.0 data is available for this CVE.
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Feb 5, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-532 | Insertion of Sensitive Information into Log File | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| agpt autogpt platform | < 0.6.46 |
CPE
Remediation
| |
Change History
4 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jun 17, 2026 | CVE Modified | [email protected] |
| Jun 17, 2026 | CVE Modified | CISA-ADP |
| Feb 17, 2026 | Initial Analysis | [email protected] |
| Feb 4, 2026 | New CVE Received | [email protected] |