CVE-2025-22603 AutoGPT SSRF vulnerability

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Versions prior to autogpt-platform-beta-v0.4.2 contains a server-side request forgery SSRF vulnerability inside component or block Send Web Request. The...

AutoGPT 代码问题漏洞

AutoGPT is a tool from AutoGPT Open Source. Used to enable everyone to use and build accessible AI. A code issue vulnerability exists in versions prior to AutoGPT autogpt-platform-beta-v0.4.2, which stems from a Send Web Request component that could lead to server-side request forgery...

CVE-2024-1880

An OS command injection vulnerability exists in the MacOS Text-To-Speech class MacOSTTS of the significant-gravitas/autogpt project, affecting versions up to v0.5.0. The vulnerability arises from the improper neutralization of special elements used in an OS command within the speech method of the...

CVE-2024-1879

A Cross-Site Request Forgery CSRF vulnerability in significant-gravitas/autogpt version v0.5.0 allows attackers to execute arbitrary commands on the AutoGPT server. The vulnerability stems from the lack of protections on the API endpoint receiving instructions, enabling an attacker to direct a us...

CVE-2024-1881

AutoGPT, a component of significant-gravitas/autogpt, is vulnerable to an improper neutralization of special elements used in an OS command 'OS Command Injection' due to a flaw in its shell command validation function. Specifically, the vulnerability exists in versions v0.5.0 up to but not...

The vulnerability of the AutoGPT library, related to its failure to take measures to neutralize special elements, allows a violator to bypass the restrictions on shell commands.

The vulnerability of the AutoGPT library is related to the failure to take measures to neutralize certain elements. Exploiting this vulnerability allows a remote attacker to bypass the restrictions in the botnet’s command list...

AutoGPT SSTI Vulnerability Leading to Remote Code Execution (RCE)

Summary AutoGPT, an open-source AI tool that automates task execution, is vulnerable to a Server-Side Template Injection SSTI that could lead to arbitrary command execution. The vulnerability arises from the improper handling of user-supplied format strings in the AgentOutputBlock implementation,...

SSRF Vulnerabilities found in Search and Github Integration AutoGPT Blocks

Hi, AutoGPT developers! Summary I have identified several Server-Side Request Forgery SSRF vulnerabilities in the default agent blocks provided by the AutoGPT platform. These vulnerabilities could lead to severe security issues, including credential leakage e.g., GitHub tokens, internal network...

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...

GHSA-G84Q-54HF-36RG 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-2024-6091

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 executin...

CVE-2024-6091

CVE-2024-6091 affects significant-gravitas/autogpt v0.5.1. The vulnerability allows bypassing the shell commands denylist by manipulating the command path (for example, executing “/bin/./whoami” when the denylist blocks “whoami” or “/bin/whoami”). This leads to an OS command injection risk where ...

CVE-2024-6091 Shell Command Denylist Bypass in significant-gravitas/autogpt

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 executin...

CVE-2024-6091 Shell Command Denylist Bypass in significant-gravitas/autogpt

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 executin...

CVE-2024-6091 Shell Command Denylist Bypass in significant-gravitas/autogpt

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 executin...

PT-2024-10397

Name of the Vulnerable Software and Affected Versions significant-gravitas/autogpt version 0.5.1 Description A vulnerability in significant-gravitas/autogpt allows an attacker to bypass the shell commands denylist settings. The issue arises when the denylist is configured to block specific...

CVE-2024-1880

An OS command injection vulnerability exists in the MacOS Text-To-Speech class MacOSTTS of the significant-gravitas/autogpt project, affecting versions up to v0.5.0. The vulnerability arises from the improper neutralization of special elements used in an OS command within the speech method of the...

CVE-2024-1881

AutoGPT, a component of significant-gravitas/autogpt, is vulnerable to an improper neutralization of special elements used in an OS command 'OS Command Injection' due to a flaw in its shell command validation function. Specifically, the vulnerability exists in versions v0.5.0 up to but not...

CVE-2024-1880 OS Command Injection in MacOS Text-To-Speech Class in significant-gravitas/autogpt

An OS command injection vulnerability exists in the MacOS Text-To-Speech class MacOSTTS of the significant-gravitas/autogpt project, affecting versions up to v0.5.0. The vulnerability arises from the improper neutralization of special elements used in an OS command within the speech method of the...

CVE-2024-1880 OS Command Injection in MacOS Text-To-Speech Class in significant-gravitas/autogpt

An OS command injection vulnerability exists in the MacOS Text-To-Speech class MacOSTTS of the significant-gravitas/autogpt project, affecting versions up to v0.5.0. The vulnerability arises from the improper neutralization of special elements used in an OS command within the speech method of the...