Every layer verified. Every connection authenticated. Every output stays local. ShellPilot integrates with the security controls your environment already enforces — it does not replace, route around, or downgrade them.
No chat history stored. No scripts saved. No output cached. Close the application — everything is gone. Nothing is written to disk unless you explicitly export.
Scripts execute in an embedded PS7 runspace. Output, variables, credentials never leave your machine.
Client verifies the proxy. Proxy verifies the client. ECDSA challenge-response prevents MITM attacks.
Every AI request runs through the authenticated proxy path with device-bound session credentials. Captured traffic alone cannot be replayed against another device or reused outside the active session.
Get-Credential and Read-Host -AsSecureString handled natively. Passwords encrypted in memory. Never logged, never sent to AI.
Full ScriptBlock Logging compatibility. Windows Event Log integration. Audit every script execution.
Hardware-based device fingerprints. Activation tied to physical machines. Sessions cannot be cloned or transferred.
Budget, rate limits, device count all enforced server-side. Client-side tampering cannot bypass restrictions.
Extended Validation certificate. Immediate SmartScreen trust on all Windows systems. No download warnings.
The points procurement, audit, and security reviewers usually ask about — stated precisely, without marketing gloss.
powershell.exe, pwsh.exe, or in ShellPilot's embedded runspace. App Control for Business (formerly WDAC) and AppLocker put the embedded runspace into ConstrainedLanguage mode the same way they put any other PowerShell session into it. Behavior-based EDR sees ShellPilot.exe loading the PowerShell runtime and executing scripts, and is free to act on what it observes. Application Guard, Defender ASR rules, and comparable controls do what they were configured to do. ShellPilot does not ship, document, or enable any evasion path against any of those controls — by design.
Bypass for its own session, both for the embedded runspace and for the external PowerShell launched by the yellow and red buttons. This is per-session and ends with the process; nothing on the machine or in the user profile is changed. Microsoft documents the execution policy as a guardrail against unintentional script execution, not a security boundary — "it's not a security boundary because it can't stop determined users from deliberately running scripts" (Microsoft Learn, about_Execution_Policies). A Group Policy Turn on Script Execution takes precedence for the external PowerShell path.
Read-Host, Get-Credential, and Read-Host -AsSecureString are intercepted by ShellPilot's custom PSHost. The input never appears as a chat message, never gets logged, and is never serialised into an AI request. SecureString content stays in protected memory and is handed to the runspace as a SecureString. This is a structural barrier, not a system-prompt instruction — the data never technically reaches the model on that path.
See the full data-flow architecture, or talk to us directly — we answer reviewer questions in plain terms.