CognicellAI CVE debriefs

These pages are published after PatchSiren validates generated defensive summaries against stored public CVE and source evidence.

CRITICAL CognicellAI CVE published 2026-10-19

CVE-2026-109437

CVE-2026-109437 debrief: Cognition before 0.13.0 has a critical unauthenticated remote code execution vulnerability due to its agent sandbox backend defaulting to local execution and lacking REST/SSE API authentication. This vulnerability allows attackers to create sessions and post messages without credentials, leading to potential remote code execution as the server process. Defenders should assess expo [truncated]