Threat database

DB-GPT through 0.8.2 contains an unauthenticated remote code execution vulnerability because the /api/v1/chat/react-agent endpoint relies on a mock get_user_from_headers function that grants every caller the admin role. Unauthenticated attackers can send prompts that make the ReAct agent's unsandboxed code_interpreter and shell_interpreter tools run arbitrary Python or bash as root in the webserver container, including reaching the bundled database with default credentials.

A vulnerability has been found in eosphoros-ai DB-GPT up to 0.7.5. This issue affects the function module_plugin.refresh_plugins of the file packages/dbgpt-serve/src/dbgpt_serve/agent/hub/controller.py of the component FastAPI Endpoint. Such manipulation leads to unrestricted upload. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.

In eosphoros-ai/db-gpt version v0.6.0, the web API `POST /v1/personal/agent/upload` is vulnerable to Arbitrary File Upload with Path Traversal. This vulnerability allows unauthorized attackers to upload arbitrary files to the victim's file system at any location. The impact of this vulnerability includes the potential for remote code execution (RCE) by writing malicious files, such as a malicious `__init__.py` in the Python's `/site-packages/` directory.