Vulnerability · Published Feb 4, 2026 · Assigned by GitHub_M

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

High 8.1

In plain English

A high-severity sensitive data in logs in AutoGPT from Significant-Gravitas. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 42% of all known vulnerabilities). Ready-made attack tooling exists: public proof-of-concept code.

Severity (CVSS 3.1)8.1High

Exploit odds (30 days)0.5%top 57.9% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack tooling1Public PoC

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.

Affected products (as reported)

Vendor	Product	Versions
Significant-Gravitas	AutoGPT	< autogpt-platform-beta-v0.6.46

Weakness: CWE-532 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rc89-6g7g-v5v7 x_refsource_CONFIRM
https://github.com/Significant-Gravitas/AutoGPT/commit/1eabc604842fa876c09d69af43d2d1e8fb9b8eb9 x_refsource_MISC