Vulnerabilidades de Agpt
CVEs publicadas que afetam produtos de Agpt: 8 registro(s), com severidade, exploração e correções.
CVE-2025-32425
Média · 5.5
CWE-770 13/05/2026
AutoGPT has missing Docker log rotation on platform containers that allows host disk-exhaustion DoS
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. In AutoGPT, the execution process is recorded to the console (stdout/stderr), and deployed in container mode, which is automatically captured by Docker and stored as "container logs". However, prior to 0.6.32, there is no limit on the log size when the container is deployed. When the number of user accesses is too large, the log on the server disk will be too large, causing disk resource exhaustion and eventually causing DoS. autogpt-platform-beta-v0.6.32 fixes the issue.
CVE-2026-26020
Alta · 8.8
CWE-285 12/02/2026
AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to 0.6.48, an authenticated user could achieve Remote Code Execution (RCE) on the backend server by embedding a disabled block inside a graph. The BlockInstallationBlock — a development tool capable of writing and importing arbitrary Python code — was marked disabled=True, but graph validation did not enforce this flag. This allowed any authenticated user to bypass the restriction by including the block as a node in a graph, rather than calling the block's execution endpoint directly (which did enforce the flag). This vulnerability is fixed in 0.6.48.
CVE-2026-26006
Média · 6.5
CWE-1333 10/02/2026
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.
CVE-2025-32393
Média · 6.5
CWE-770 05/02/2026
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 file according to the URL input by the user, parse the XML, and finally obtain the parsed result. However, during the parsing process, there is no limit on the parsing time and the resources that can be allocated for parsing. When a malicious user lets RSSBlock parse a carefully constructed, deep XML, it will cause memory resources to be exhausted, eventually causing DoS. This issue has been patched in autogpt-platform-beta-v0.6.32.
CVE-2026-22038
Alta · 8.1
CWE-532 04/02/2026
AutoGPT's API Keys and Secrets Logged in Plaintext in Stagehand Integration Blocks
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 logger.info() statements. This occurs in three separate block implementations (StagehandObserveBlock, StagehandActBlock, and StagehandExtractBlock) where the code explicitly calls api_key.get_secret_value() and logs the result. This issue has been patched in autogpt-platform-beta-v0.6.46.
CVE-2025-62616
Crítica · 9.8
CWE-918 04/02/2026
SSRF no SendDiscordFileBlock da AutoGPT Platform
O AutoGPT é uma plataforma que permite aos usuários criar, implantar e gerenciar agentes contínuos de inteligência artificial que automatizam fluxos de trabalho complexos. Antes de autogpt-platform-beta-v0.6.34, no SendDiscordFileBlock, a biblioteca de terceiros aiohttp.ClientSession().get é usada diretamente para acessar a URL, mas a URL de entrada não é filtrada, o que causa uma vulnerabilidade de SSRF. Este problema foi corrigido em autogpt-platform-beta-v0.6.34.
CVE-2025-62615
Crítica · 9.8
CWE-918 04/02/2026
SSRF no RSSFeedBlock do AutoGPT Platform
AutoGPT é uma plataforma que permite aos usuários criar, implantar e gerenciar agentes contínuos de inteligência artificial que automatizam fluxos de trabalho complexos. Antes da versão autogpt-platform-beta-v0.6.34, no RSSFeedBlock, a biblioteca de terceiros urllib.request.urlopen é usada diretamente para acessar a URL, mas a URL de entrada não é filtrada, o que causa uma vulnerabilidade de SSRF. Este problema foi corrigido na autogpt-platform-beta-v0.6.34.
CVE-2026-24780
Alta · 8.8
CWE-94 29/01/2026
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 without checking the `disabled` flag. Any authenticated user can execute the disabled `BlockInstallationBlock`, which writes arbitrary Python code to the server filesystem and executes it via `__import__()`, achieving Remote Code Execution. In default self-hosted deployments where Supabase signup is enabled, an attacker can self-register; if signup is disabled (e.g., hosted), the attacker needs an existing account. autogpt-platform-beta-v0.6.44 contains a fix.