Skip to content
Fencer Intel
high 8.1

CVE-2026-22038 json

AutoGPT's API Keys and Secrets Logged in Plaintext in Stagehand Integration Blocks

published 9mo ago modified 4mo ago also EUVD-2026-5543

cvss
8.1
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.5%
EPSS 0.5% chance of exploitation in 30 days, percentile 42%
public exploits
0
none known

Summary

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.

Patch / fix

  • agpt autogpt 0.6.46
  • agpt autogpt_platform 0.6.46
  • agpt autogpt_platform_backend 0.6.46

Is CVE-2026-22038 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
9mo ago

Exploit prediction

0.49% chance of exploitation in the next 30 days, higher than 42% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • github.com https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rc89-6g7g-v5v7 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 8.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

Affected products

  • Significant-Gravitas AutoGPT

Classification

Weakness
  • CWE-532 Insertion of Sensitive Information into Log File

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.