PT-2026-7904

Name of the Vulnerable Software and Affected Versions AutoGPT versions prior to 0.6.48 Description AutoGPT is a platform for creating and managing AI agents to automate workflows. An authenticated user could achieve Remote Code Execution RCE on the backend server. This occurred because the...

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...

CVE-2025-32393

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.32, there is a DoS vulnerability in ReadRSSFeedBlock. In RSSBlock, feedparser.parser is called to obtain the XML fil...

CVE-2025-62616

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.34, in SendDiscordFileBlock, the third-party library aiohttp.ClientSession.get is used directly to access the URL, b...

CVE-2026-22038

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.46, the AutoGPT platform's Stagehand integration blocks log API keys and authentication secrets in plaintext using...

CVE-2025-32393

AutoGPT exposes a DoS in ReadRSSFeedBlock where feedparser.parser may parse deeply nested XML without limits on time or resources, exhausting memory and causing service disruption. Multiple sources (Red Hat and NVD/NVD-derived entries) confirm the issue and note it affects autogpt-platform-beta-v...

CVE-2025-32393

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.32, there is a DoS vulnerability in ReadRSSFeedBlock. In RSSBlock, feedparser.parser is called to obtain the XML fil...

CVE-2025-32393 AutoGPT has a DoS vulnerability in ReadRSSFeedBlock

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.32, there is a DoS vulnerability in ReadRSSFeedBlock. In RSSBlock, feedparser.parser is called to obtain the XML fil...

CVE-2026-22038

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.46, the AutoGPT platform's Stagehand integration blocks log API keys and authentication secrets in plaintext using...

CVE-2025-62616

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.34, in SendDiscordFileBlock, the third-party library aiohttp.ClientSession.get is used directly to access the URL, b...

CVE-2025-62615

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.34, in RSSFeedBlock, the third-party library urllib.request.urlopen is used directly to access the URL, but the inpu...

CVE-2025-62616

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.34, in SendDiscordFileBlock, the third-party library aiohttp.ClientSession.get is used directly to access the URL, b...

CVE-2025-62615

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.34, in RSSFeedBlock, the third-party library urllib.request.urlopen is used directly to access the URL, but the inpu...

CVE-2026-24780 AutoGPT is Vulnerable to RCE via Disabled Block Execution

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.44, AutoGPT Platform's block execution endpoints both main web API and external API allow executing blocks by UUID...

CVE-2026-24780 AutoGPT is Vulnerable to RCE via Disabled Block Execution

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.44, AutoGPT Platform's block execution endpoints both main web API and external API allow executing blocks by UUID...

EUVD-2025-14755

Malicious code in bioql PyPI...

EUVD-2025-14754

Malicious code in bioql PyPI...

CVE-2025-53944 AutoGPT Platform Exposes Graph Execution Results via Authorization Gap

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents. In v0.6.15 and below, the external API's getgraphexecutionresults endpoint has an authorization bypass vulnerability. While it correctly validates user access to the graphid, it fails ...

CVE-2025-53944

CVE-2025-53944 concerns AutoGPT. In v0.6.15 and earlier, the external API endpoint get_graph_execution_results bypassed authorization by validating graph_id ownership but not graph_exec_id ownership, allowing authenticated users to access arbitrary execution results. The internal API properly val...

CVE-2025-53944 AutoGPT Platform Exposes Graph Execution Results via Authorization Gap

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents. In v0.6.15 and below, the external API's getgraphexecutionresults endpoint has an authorization bypass vulnerability. While it correctly validates user access to the graphid, it fails ...