CVE-2026-109437 Cognition < 0.13.0 Unauthenticated RCE via Local Shell Backend
Unauthenticated attackers can execute arbitrary shell commands on the server by sending messages to the AI agent's API without credentials.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-109437?
CVE-2026-109437 is a critical authentication bypass vulnerability in CognicellAI Cognition, published on 19 Oct 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Which versions are affected by CVE-2026-109437?
How do I fix CVE-2026-109437?
No fix has been published for CVE-2026-109437 yet. Limit exposure of the affected software until one is available.
Upgrade, and rotate credentials and sessions that may have been exposed. More about Authentication bypass.
Is CVE-2026-109437 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-109437 exists.
Sources
Also known as GHSA-c2qr-crjw-844g.