Cognition before 0.13.0 contains an unauthenticated remote code execution vulnerability due to defaulting its agent sandbox backend to local execution and shipping no authentication on its REST/SSE API. Attackers can create a session via POST /sessions and post a message via POST /sessions/{id}/messages without credentials, causing the Deep Agents ReAct loop to run attacker-directed shell commands through the local shell backend, resulting in remote code execution as the server process.
Upgrade to Cognition 0.13.0 or later. Version 0.13.0 refuses the local sandbox backend unless COGNITION_ALLOW_UNSAFE_LOCAL_EXECUTION is explicitly set to true, and that setting defaults to false.