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

High 8.1 Published 4 Feb 2026 Updated 5 Feb 2026

Attackers with log access can steal API keys and secrets from AutoGPT Stagehand integration blocks due to plaintext logging.

Exploited in the wild: Not known
Login needed: Any signed-in user
Attackable: Over the internet
Victim action needed: Not needed
Fix: None listed

What is CVE-2026-22038?

CVE-2026-22038 is a high-severity vulnerability in Significant-Gravitas AutoGPT, published on 4 Feb 2026. Any signed-in user can exploit it over the network, with no action from the victim.

Official 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.

Weakness: CWE-532

Which versions are affected by CVE-2026-22038?

It affects 1 product.

Products include Agpt Autogpt Platform.

How do I fix CVE-2026-22038?

No fix has been published for CVE-2026-22038 yet. Limit exposure of the affected software until one is available.

Is CVE-2026-22038 being exploited?

There is no known exploitation of CVE-2026-22038 in the wild and no public exploit code.

Public exploit code: 1 proofs of concept on GitHub.

Sources

Also known as GHSA-rc89-6g7g-v5v7.