| Titre | GH05TCREW pentestagent v1.0 RCE |
|---|
| Description | PentestAgent's default execution runtime (LocalRuntime) executes shell commands generated by the LLM agent using asyncio.create_subprocess_shell with no command validation, no sandboxing, and no filesystem isolation. The LLM generates commands based on tool outputs that include data from the target system — outputs that may contain prompt-injection content. Because the default runtime executes these commands directly on the host, a target system that injects malicious instructions into its output (e.g., HTTP response bodies, SSH banners, DNS records) can cause arbitrary commands to execute on the operator's machine. |
|---|
| La source | ⚠️ https://github.com/GH05TCREW/pentestagent/issues/91 |
|---|
| Utilisateur | ez-lbz (UID 87033) |
|---|
| Soumission | 04/08/2026 09:53 (il y a 1 mois) |
|---|
| Modérer | 12/09/2026 22:02 (1 month later) |
|---|
| Statut | Accepté |
|---|
| Entrée VulDB | 403199 [GH05TCREW PentestAgent LocalRuntime runtime/runtime.py LocalRuntime.execute_command élévation de privilèges] |
|---|
| Points | 20 |
|---|