Read the docs
TI-2026-17732 Aliases CVE-2026-22038

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

Priority LOW 36CWE-532Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Impact type
Information disclosure
Confidentiality · integrity · availability
High · None · High
Fix status
No fix listed

Attack profile from CVSS 3.1 · CNA. Fix status from CNA. Impact type from CWE-532.

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00487 42nd percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix No fix listed No fixed version in the sources yet

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
Significant-GravitasAutoGPT< autogpt-platform-beta-v0.6.46—No fix listedCNA
  • AutoGPT VendorSignificant-Gravitas Affected < autogpt-platform-beta-v0.6.46 Fixed in — No fix listed CNA

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:*before 0.6.46VulnerableSignificant-Gravitas
  • cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:* Versions before 0.6.46 Vulnerable ·Significant-Gravitas

Remediation

No fixed version listed by the sources yet.

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-22038

References

Exploit 1

Patch 1

  • TI-2026-19981 AutoGPT is Vulnerable to RCE via Disabled Block Execution CVSS 4.0HIGH 8.6
  • TI-2025-23471 AutoGPT has a DoS vulnerability in ReadRSSFeedBlock CVSS 4.0HIGH 8.7
  • TI-2025-22672 AutoGPT allows leakage of cross-domain cookies and protected headers in requests redirect CVSS 3.1HIGH 8.6
  • TI-2025-16489 AutoGPT SSRF vulnerability CVSS 4.0HIGH 7.7
  • TI-2025-00879 Server-Side Template Injection (SSTI) in significant-gravitas/autogpt CVSS 3.1HIGH 8.8
  • TI-2025-22671 AutoGPT allows SSRF due to DNS Rebinding in requests wrapper CVSS 3.1HIGH 7.5
See all 14 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences