| Título | ipa-lab hackingBuddyGPT v1.0 RCE |
|---|
| Descripción | HackingBuddyGPT is an LLM-driven pentest agent that uses an SSH connection to interact with a target machine. The raw output from commands executed on the target is captured and appended to the LLM's conversation history without any sanitization or taint marking. A compromised target can embed prompt-injection text in its command output (e.g., in shell motd, CLI tool output, or filesystem contents). When the LLM processes this injected context, it can be directed to generate arbitrary shell commands. These commands are then executed on the operator's local workstation via tmux send-keys, not in a sandbox — resulting in remote code execution on the operator's machine. |
|---|
| Fuente | ⚠️ https://github.com/ipa-lab/hackingBuddyGPT/issues/150 |
|---|
| Usuario | ez-lbz (UID 87033) |
|---|
| Sumisión | 2026-08-04 10:19 (hace 1 mes) |
|---|
| Moderación | 2026-09-12 22:22 (1 month later) |
|---|
| Estado | Aceptado |
|---|
| Entrada de VulDB | 403203 [ipa-lab HackingBuddyGPT hasta 0.5.0 ssh_run_command.py ssh_run_command escalada de privilegios] |
|---|
| Puntos | 20 |
|---|