PT-2026-7472 · Autogpt · Autogpt

Ltduc147 · Published 2026-02-10 · Updated 2026-02-11 · CVE-2026-26006

Positive Technologies (AI Summary)

CVSS v3.1

6.5

Medium

Base vector

AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Name of the Vulnerable Software and Affected Versions AutoGPT versions prior to 0.6.32

Description AutoGPT is a platform for creating, deploying, and managing continuous artificial intelligence agents that automate complex workflows. Versions of AutoGPT before 0.6.32 contain a Regular Expression Denial of Service issue due to the use of regular expressions in the Code Extraction Block. Specifically, the regular expressions s+[sS]*? and s+(.*?) are vulnerable. These expressions contain adjacent quantifiers that can match the same space character (s), allowing an attacker to provide a long sequence of space characters to trigger excessive regex backtracking, potentially leading to a Denial of Service (DoS).

Recommendations Update to version 0.6.32 or later.

Exploit

Fix

DoS

Weakness Enumeration

CWE-1333

Related Identifiers

CVE-2026-26006

GHSA-M2WR-7M3R-P52C

Affected Products

Autogpt

References · 11

• 🔥 https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/26xxx/CVE-2026-26006.json · Exploit
• https://github.com/Significant-Gravitas/AutoGPT/commit/57a06f70883ce6be18738c6ae8bb41085c71e266 · Patch
• https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-m2wr-7m3r-p52c · Vendor Advisory
• https://nvd.nist.gov/vuln/detail/CVE-2026-26006 · Security Note
• https://osv.dev/vulnerability/CVE-2026-26006 · Vendor Advisory
• https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.32 · Note
• https://github.com/Significant-Gravitas/AutoGPT/blob/master/autogpt_platform/backend/backend/blocks/code_extraction_block.py#L106-L109 · Note
• https://github.com/Significant-Gravitas/AutoGPT/blob/master/autogpt_platform/backend/backend/blocks/code_extraction_block.py#L86-L96 · Note
• https://twitter.com/CVEnew/status/2021365283785474247 · Twitter Post
• https://twitter.com/VulmonFeeds/status/2021424187387117855 · Twitter Post
• https://t.me/CVEtracker/44358 · Telegram Post