Denial of Service in AutoGPT AITextSummarizerBlock

Executive Summary

The CVE-2025-32394 vulnerability is a denial-of-service (DoS) issue in the AITextSummarizerBlock of AutoGPT, specifically in the chunking mechanism of the _split_text function in llm.py.

Malicious users can exploit this vulnerability by manipulating the max_tokens and overlap parameters, which are user-controlled inputs, to cause quadratic memory amplification.

For example, an input of 10KB can cause the server to consume up to 50GB of memory, exhausting memory resources and resulting in a DoS condition.

This vulnerability affects versions of AutoGPT up to 0.6.31 and was fixed in version 0.6.32.

Useful 0 Not Useful 0

Detection Guidance

This vulnerability can be detected by monitoring for unusually high memory consumption by the AutoGPT process, especially when processing inputs to the AITextSummarizerBlock. Since the issue involves the `max_tokens` and `overlap` parameters being manipulated to cause excessive memory use, checking these parameters in use or logs may help identify exploitation attempts.

There are no specific commands provided to detect this vulnerability directly, but general system monitoring commands can be used to observe memory usage spikes during AutoGPT operation.

• Use `top` or `htop` to monitor memory usage of the AutoGPT process in real time.
• Use `ps aux --sort=-%mem | grep autogpt` to identify if AutoGPT is consuming excessive memory.
• Check application logs for unusually large inputs or abnormal values for `max_tokens` and `overlap` parameters.

Useful 0 Not Useful 0

Impact Analysis

This vulnerability can lead to a denial-of-service (DoS) condition by exhausting the server's memory resources.

An attacker can cause the system to consume excessive memory, potentially making the AutoGPT service unavailable to legitimate users.

This can disrupt workflow automation processes that rely on AutoGPT, causing downtime and impacting business operations.

Useful 0 Not Useful 0

Compliance Impact

There is no information provided in the available context or resources about how this vulnerability affects compliance with common standards and regulations such as GDPR or HIPAA.

Useful 0 Not Useful 0

Mitigation Strategies

The immediate mitigation step is to upgrade AutoGPT to version 0.6.32 or later, where this vulnerability has been fixed.

Until the upgrade can be applied, restrict or validate user inputs to the AITextSummarizerBlock, especially limiting the `max_tokens` and `overlap` parameters to prevent memory amplification.

Additionally, monitor system memory usage closely to detect and respond to potential denial-of-service conditions caused by this vulnerability.

Useful 0 Not Useful 0