| Title | 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. |
|---|
| Source | ⚠️ https://github.com/GH05TCREW/pentestagent/issues/91 |
|---|
| User | ez-lbz (UID 87033) |
|---|
| Submission | 08/04/2026 09:53 (1 month ago) |
|---|
| Moderation | 09/12/2026 22:02 (1 month later) |
|---|
| Status | Accepted |
|---|
| VulDB entry | 403199 [GH05TCREW PentestAgent up to cf882dabea3ed91cef016cdd115e5426315665a2 LocalRuntime runtime/runtime.py LocalRuntime.execute_command os command injection] |
|---|
| Points | 20 |
|---|