Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2025-32423— AutoGPT: There is a DoS vulnerability in ExtractTextInformationBlock

Quick assessment

Affected
Significant-Gravitas AutoGPT
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Significant-Gravitas AutoGPT是Significant-Gravitas的人工智能软件。 Significant-Gravitas AutoGPT 0.6.32之前版本存在资源管理错误漏洞，该漏洞源于ExtractTextInformationBlock功能中可被恶意用户输入放大，导致服务器消耗大量内存资源，最终造成拒绝服务（DoS）。

AI Predicted 7.5 Difficulty: Easy EPSS 0.31% · P21

Possible ATT&CK Techniques 1 AI

T1499 · Endpoint Denial of Service

Affected Version Matrix 1

VendorProduct Version RangeStatus
Significant-Gravitas AutoGPT < 0.6.32 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-32423

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
AutoGPT: There is a DoS vulnerability in ExtractTextInformationBlock
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
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
Source: CVE Program / CVE List V5
Vulnerability Type
不加限制或调节的资源分配
Source: CVE Program / CVE List V5
Vulnerability Title
Significant-Gravitas AutoGPT 资源管理错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Significant-Gravitas AutoGPT是Significant-Gravitas的人工智能软件。 Significant-Gravitas AutoGPT 0.6.32之前版本存在资源管理错误漏洞，该漏洞源于ExtractTextInformationBlock功能中可被恶意用户输入放大，导致服务器消耗大量内存资源，最终造成拒绝服务（DoS）。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
Significant-Gravitas AutoGPT < 0.6.32 -

II. Public POCs for CVE-2025-32423

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2025-32423

请登录查看更多情报信息。

Vendor Advisories for CVE-2025-32423 (1)

Same Patch Batch · Significant-Gravitas · 2026-06-26 · 4 CVEs total

CVE-2026-56663 8.5 HIGH AutoGPT: SSRF-to-RCE Chain in `SendWebRequestBlock` via IP validation bypass and internal
CVE-2026-56823 5.4 MEDIUM AutoGPT: IDOR in Webhook Ping Endpoint Allows Enumeration and Cross-User Ping Triggering
CVE-2025-32394 AutoGPT: There is a DoS vulnerability in AITextSummarizerBlock

IV. Related Vulnerabilities

Same product: AutoGPT
Same vendor: Significant-Gravitas
Same weakness: CWE-770

V. Comments for CVE-2025-32423

No comments yet

Leave a comment