AgenticSeek vulnerabilities

AgenticSeek before commit 409840c contains a remote code execution vulnerability because llm_server/app.py hardcodes Flask debug mode while binding to all interfaces. An attacker who reaches the server port and obtains the derivable Werkzeug debugger PIN can execute Python code and operating system commands with llm_server privileges.

AgenticSeek (commit fc242c7) contains an unauthenticated remote code execution vulnerability that allows any network-adjacent attacker to execute arbitrary commands by submitting crafted queries to the unprotected POST /query API endpoint bound to 0.0.0.0:7777 with wildcard CORS. Attackers can send unauthenticated HTTP requests that cause the autonomous agent to generate and execute shell commands through BashInterpreter using subprocess.Popen with shell=True and safety=False, bypassing the incomplete command blocklist to achieve full host-level code execution.

A vulnerability has been found in Fosowl agenticSeek 0.1.0 affecting the function PyInterpreter.execute in the file sources/tools/PyInterpreter.py of the query Endpoint component. Such manipulation leads to code injection. The attack can be launched 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.