| Título | Simular AI Agent-S 0.3.2 Denial of Service |
|---|
| Descrição | Agent-S CodeAgent contains a denial of service vulnerability in its local tool execution workflow. When local code execution is enabled, a crafted task prompt can induce CodeAgent to execute model-generated Python code. The Python subprocess is run without an effective timeout, memory budget, or stdout/stderr output-size limit, and its output is fully buffered before being returned to the agent.
An attacker can cause high-volume output or memory-consuming Python execution through a normal task prompt, exhausting the worker process memory and terminating the agent service. In a deployed agent environment, this can interrupt normal task execution and make the service unavailable to legitimate users. |
|---|
| Fonte | ⚠️ https://github.com/outlookgp/CVE/tree/main/AgentS_CodeAgent_Tool_Output_DoS_Report |
|---|
| Utilizador | outlookgp (UID 99658) |
|---|
| Submissão | 11/07/2026 13h32 (há 2 meses) |
|---|
| Moderação | 02/09/2026 16h16 (2 months later) |
|---|
| Estado | Aceite |
|---|
| Entrada VulDB | 398133 [simular-ai Agent-S 0.3.1/0.3.2 CodeAgent code_agent.py Negação de Serviço] |
|---|
| Pontos | 20 |
|---|