Credential disclosure via plaintext Stagehand logging
Published Feb 4, 2026 · Updated Feb 4, 2026
Sensitive-data exposure in AutoGPT before autogpt-platform-beta-v0.6.46 allows remote authenticated users to read API keys from logs. The StagehandObserveBlock, StagehandActBlock, and StagehandExtractBlock call get_secret_value() and pass plaintext keys to logger.info(). Log-read access and prior execution of a Stagehand block are required; exposed keys grant only the access and quotas assigned by their providers.
Summary
What happened
Sensitive-data exposure in AutoGPT before autogpt-platform-beta-v0.6.46 allows remote authenticated users to read API keys from logs. The StagehandObserveBlock, StagehandActBlock, and StagehandExtractBlock call get_secret_value() and pass plaintext keys to logger.info(). Log-read access and prior execution of a Stagehand block are required; exposed keys grant only the access and quotas assigned by their providers.
The record
- CVE
- CVE-2026-22038
- Published
- Feb 4, 2026
- Updated
- Feb 4, 2026
- Vendor
- Significant Gravitas
- Product
- AutoGPT
- Classifications
- CWE-532, T1552.001
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Feb 4, 2026CVE publishedPublication date reported by the CVE source.
- Feb 4, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< autogpt-platform-beta-v0.6.46
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Stagehand plaintext-log proof of conceptproof of concept · unverified
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo