CVE WatchOct 19, 2026

CVE-2026-109437

Cognition before 0.13.0 contains an unauthenticated remote code execution vulnerability due to defaulting its agent sandbox backend to local

CVSS

9.8

Critical

EPSS

—

KEV

—

Exploit Today

0-100

Published: Oct 19, 2026 · Last modified: Oct 19, 2026 · CWE-306 · CWE-1188

EPSS · 30d

Not enough EPSS history yet.

Technical 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.

Official references

Related CVEs

CVECVSSEPSSKEVRExploitTitleMod.

CVE-2026-75753—

—

——0Missing Authentication for a Critical Function in certain ASUS routers allows an unauthorized nearby user to send specific commands via HTTP requests, causing the router to return device identification information and switch into a specific mode. As a result, when the router encounters abnormal conditions, it may be unable to perform self-recovery. Refer to the ' Security Update for ASUS Router Firmware' section on the ASUS Security Advisory for more information.9h CVE-2026-779369.8 CRI

—

——0Letta through 0.16.8 ships a compose.yaml that does not enable LETTA_SERVER_SECURE, so the password middleware is never added and all API routes are unauthenticated, and it exposes a superuser PostgreSQL port with default credentials. Remote attackers can execute arbitrary Python via POST /v1/tools/run, manage /v1/admin users, or run OS commands via COPY PROGRAM.10h CVE-2026-779348.8 HIG

—

——0Coze Studio before 0.5.0 contains an insecure default configuration that allows any registered user to execute commands by running workflow code nodes in an unsandboxed python3 subprocess. Attackers can bypass the regex import filter with __import__('subprocess') to run commands, stealing environment variables, model API keys, and accessing MySQL, MinIO, Redis and etcd.10h CVE-2026-779329.8 CRI

—

——0DB-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.10h CVE-2026-751289.8 CRI

—

——0Langchain-Chatchat through 0.3.1.3 exposes a POST /tools/call API endpoint that invokes any registered tool by name without authentication, leaving the always-registered shell tool callable. Remote attackers can send a single request naming the shell tool to execute arbitrary OS commands as the server user (root in the shipped Docker image).10h CVE-2026-1094429.8 CRI

—

——0piflow 2.0.0 through 2.0.1 contains a remote code execution vulnerability in its DeepAgents chat agent, whose POST /chat and POST /chat/stream endpoints lack authentication. Attackers can instruct the agent to call the exec_shell tool, which runs arbitrary commands via subprocess.run without human approval or an allow-list, exposing environment secrets such as LLM API keys and database credentials.10h