CVE-2026-22038
Sensitive Data Exposure in AutoGPT Stagehand Blocks via Logging
Publication date: 2026-02-04
Last updated on: 2026-02-17
Assigner: GitHub, Inc.
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| agpt | autogpt_platform | to 0.6.46 (exc) |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-532 | The product writes sensitive information to a log file. |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
This vulnerability exists in the AutoGPT platform prior to version autogpt-platform-beta-v0.6.46. The platform's Stagehand integration improperly logs sensitive information such as API keys and authentication secrets in plaintext using logger.info() statements. Specifically, three block implementations (StagehandObserveBlock, StagehandActBlock, and StagehandExtractBlock) explicitly call api_key.get_secret_value() and log the secret values, exposing them in logs.
How can this vulnerability impact me? :
The vulnerability can lead to the exposure of sensitive API keys and authentication secrets through log files. This exposure can allow unauthorized parties to access or misuse these credentials, potentially leading to unauthorized access to systems, data breaches, or disruption of services.
How does this vulnerability affect compliance with common standards and regulations (like GDPR, HIPAA)?:
I don't know
How can this vulnerability be detected on my network or system? Can you suggest some commands?
I don't know
What immediate steps should I take to mitigate this vulnerability?
To mitigate this vulnerability, you should upgrade the AutoGPT platform to version autogpt-platform-beta-v0.6.46 or later, where the issue has been patched.