CVE-2025-32423

AutoGPT: There is a DoS vulnerability in ExtractTextInformationBlock

Published Jun 26, 2026 CVSS 4.0 · 5.3 Medium EPSS < 1% KEV · Not listed
Description
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in ExtractTextInformationBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the server will consume 50G of memory, eventually causing memory resources to be exhausted, resulting in DoS. This vulnerability is fixed in 0.6.32.

Analysis

AI-generated

Technical impact

The vulnerability in AutoGPT’s ExtractTextInformationBlock allows malicious content to be provided such that the server consumes disproportionate memory, eventually exhausting resources and causing a denial of service. The primary impact is that an attacker can disrupt the availability of the platform, affecting all users relying on the automated agent service. This weakness corresponds to CWE-770, which denotes an uncontrolled resource consumption flaw.

Affected Systems

The affected product is Significant‑Gravitas AutoGPT, versions prior to 0.6.32. An attacker could target any deployment of AutoGPT that exposes the ExtractTextInformationBlock functionality—such as the community or enterprise releases that do not yet incorporate the 0.6.32 update.

Risk and Exploitability

The CVSS score of 5.3 indicates moderate severity, and the lack of an EPSS score suggests that publicly known exploitation data is limited or not available. The vulnerability is not listed in CISA’s KEV catalog. The likely attack vector is an external user submitting a large payload to the ExtractTextInformationBlock endpoint; based on the description, the attacker can perpetrate the DoS remotely via the platform’s network interface, provided the endpoint is reachable. No additional prerequisites beyond sending the input are mentioned, so the exploitation condition appears straightforward for an attacker with network access to the AutoGPT instance.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade AutoGPT to version 0.6.32 or later, which includes the fix for the memory consumption issue.
  • Add input size limits to the ExtractTextInformationBlock API to restrict memory usage of large payloads, mitigating DoS risk during the upgrade window.
  • Implement monitoring and alerting for abnormal memory consumption to detect promptly.

Generated by OpenCVE AI on June 26, 2026 at 18:01 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Significant-gravitas
Significant-gravitas autogpt
Vendors & Products Significant-gravitas
Significant-gravitas autogpt
Type Values Removed Values Added
Description AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in ExtractTextInformationBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the server will consume 50G of memory, eventually causing memory resources to be exhausted, resulting in DoS. This vulnerability is fixed in 0.6.32.
Title AutoGPT: There is a DoS vulnerability in ExtractTextInformationBlock
Weaknesses CWE-770
References
Metrics cvssV4_0

{'score': 5.3, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N'}

Weaknesses
  • CWE-770

    Allocation of Resources Without Limits or Throttling

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Jun 29, 2026, 1:29 PM
Reserved
Apr 8, 2025, 10:54 AM
Status
Deferred
Published
Jun 26, 2026, 5:16 PM
Modified
Sep 29, 2026, 7:10 PM