CVE-2026-26006: Redos (Regular Expression Denial of Service) at Code Extraction Block in significant-gravitas/autogpt
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. The autogpt before 0.6.32 is vulnerable to Regular Expression Denial of Service due to the use of regex at Code Extraction Block. The two Regex are used containing the corresponding dangerous patterns \s+[\s\S]? and \s+(.?). They share a common characteristic — the combination of two adjacent quantifiers that can match the same space character (\s). As a result, an attacker can supply a long sequence of space characters to trigger excessive regex backtracking, potentially leading to a Denial of Service (DoS). This vulnerability is fixed in 0.6.32.
Affected Software
Remediation
Event History
Frequently Asked Questions
What is the severity of CVE-2026-26006?
CVE-2026-26006 is classified as a Regular Expression Denial of Service (ReDoS) vulnerability.
How do I fix CVE-2026-26006?
To fix CVE-2026-26006, upgrade AutoGPT to version 0.6.32 or later.
What software is affected by CVE-2026-26006?
CVE-2026-26006 affects the significant-gravitas/autogpt software versions prior to 0.6.32.
What is the impact of CVE-2026-26006?
The impact of CVE-2026-26006 includes potential denial of service due to regular expression processing inefficiencies.
When was CVE-2026-26006 discovered?
CVE-2026-26006 was identified in versions of AutoGPT released before 0.6.32.