Unrated severityNVD Advisory· Published Feb 4, 2026· Updated Feb 5, 2026
AutoGPT's API Keys and Secrets Logged in Plaintext in Stagehand Integration Blocks
CVE-2026-22038
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
2< autogpt-platform-beta-v0.6.46+ 1 more
- (no CPE)range: < autogpt-platform-beta-v0.6.46
- (no CPE)range: < autogpt-platform-beta-v0.6.46
Patches
Vulnerability mechanics
References
2- github.com/Significant-Gravitas/AutoGPT/commit/1eabc604842fa876c09d69af43d2d1e8fb9b8eb9mitrex_refsource_MISC
- github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rc89-6g7g-v5v7mitrex_refsource_CONFIRM
News mentions
0No linked articles in our index yet.