CVE-2026-22038
HIGHAutoGPT <autogpt-platform-beta-v0.6.46 - Info Disclosure
Title source: llmExploitation Summary
EIP tracks 1 public exploit for CVE-2026-22038. PoCs published by sivaadityacoder.
AI-analyzed exploit summary This repository provides a detailed technical analysis of CVE-2026-22038, an information disclosure vulnerability in AutoGPT's Stagehand integration where API keys are logged in plaintext. It includes vulnerable code snippets, root cause analysis, and mitigation strategies.
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.
Exploits (1)
This repository provides a detailed technical analysis of CVE-2026-22038, an information disclosure vulnerability in AutoGPT's Stagehand integration where API keys are logged in plaintext. It includes vulnerable code snippets, root cause analysis, and mitigation strategies.
References (2)
Scores
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H