PYSEC-2026-1078 AutoGPT is Vulnerable to RCE via Disabled Block Execution

Summary AutoGPT Platform's block execution endpoints both main web API and external API allow executing blocks by UUID without checking the disabled flag. Any authenticated user can execute the disabled BlockInstallationBlock, which writes arbitrary Python code to the server filesystem and execut...

PYSEC-2026-257 AutoGPT bypass of the shell commands denylist settings

A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist settings. The issue arises when the denylist is configured to block specific commands, such as whoami and /bin/whoami. An attacker can circumvent this restriction by executing...

CVE-2026-56663

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.52, an authenticated user can bypass the SSRF / private-IP protections in SendWebRequestBlock and reach internal network services. isipblocked in...

CVE-2025-32423

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,...

CVE-2025-32394 AutoGPT: There is a DoS vulnerability in AITextSummarizerBlock

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 AITextSummarizerBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the...

CVE-2025-32394 AutoGPT: There is a DoS vulnerability in AITextSummarizerBlock

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 AITextSummarizerBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the...

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

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,...

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

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,...

CVE-2025-32423

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,...

CVE-2025-32423

AutoGPT contains a DoS vulnerability in the ExtractTextInformationBlock prior to version 0.6.32. Malicious input amplification can cause a server to consume excessive memory (e.g., 10 KB input leading to ~50 GB memory usage), exhausting resources and causing DoS. The issue is fixed in 0.6.32. Aff...

CVE-2026-56663

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.52, an authenticated user can bypass the SSRF / private-IP protections in SendWebRequestBlock and reach internal network services. isipblocked in...

CVE-2026-56823

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to , the POST /api/integrations/webhooks/webhookid/ping endpoint fetches the target webhook by primary key alone without verifying that the webhook belongs to the...

CVE-2026-56823 AutoGPT: IDOR in Webhook Ping Endpoint Allows Enumeration and Cross-User Ping Triggering

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to , the POST /api/integrations/webhooks/webhookid/ping endpoint fetches the target webhook by primary key alone without verifying that the webhook belongs to the...

CVE-2026-56823 AutoGPT: IDOR in Webhook Ping Endpoint Allows Enumeration and Cross-User Ping Triggering

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to , the POST /api/integrations/webhooks/webhookid/ping endpoint fetches the target webhook by primary key alone without verifying that the webhook belongs to the...

CVE-2026-33235

AutoGPT is vulnerable to Denial of Service in the Fill Text Template block prior to v0.6.52. Although a SandboxedEnvironment blocks certain attributes (e.g., class ), it does not cap the computational complexity or execution time of Python/Jinja2 expressions, allowing crafted inputs to exhaust CP...

CVE-2026-33235 AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service DoS attack. While the backend implements a SandboxedEnvironment to prevent...

CVE-2026-33235 AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service DoS attack. While the backend implements a SandboxedEnvironment to prevent...

PT-2026-52089

Name of the Vulnerable Software and Affected Versions AutoGPT versions prior to 0.6.52 Description The Fill Text Template block is susceptible to a Denial of Service DoS attack. Although the backend utilizes a SandboxedEnvironment to block unauthorized attribute access, such as class , it does no...

CVE-2025-32437

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, MediaDurationBlock will download and store the video in a temporary directory without deleting before all noded are done. StepThroughItemsBlock can be used t...

CVE-2025-32392

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, AutoGPT's LoopVideoBLock allows users to input a video file and process the video, such as looping it 5 times or extending the time, and finally writing it t...