fix(agent): tell the user a prefix approval leaves the sandbox

Approving a command prefix does not only stop the prompt from reappearing.
shellExecutionArgsForApproval rewrites the call to require_escalated, which
resolves to a nil sandbox engine, so the command runs unsandboxed on the host.
The engine's escalation gate is then satisfied by the PermissionGranted flag
from the approval the user just gave for the sandboxed form.

The escalation itself is deliberate and guarded: proposedCommandPrefix refuses
to offer a prefix when any other segment of the command is not known-safe,
precisely because approval covers the whole command. The defect is that the
prompt never said so. The user chose "allow command prefix for session" and got
"and also run it outside the sandbox".

So this discloses rather than removes. PermissionRequest gains
PrefixApprovalEscalates, computed by shellPrefixApprovalEscalates from the same
guards the rewrite consults, and the two prefix options append "(runs outside
the sandbox)" when it is set. Both the TUI and the ACP path carry it, since an
editor user decides on the same terms as a terminal user.

The main test asserts the disclosure and the rewrite agree on every input
rather than checking each against a fixed expectation, so the two cannot drift
apart later. Verified by mutation: reverting the helper to always-false fails
it, as does making the label unconditional.

internal/acp/permission.go

@@ -25,7 +25,7 @@ func buildPermissionOptions(req agent.PermissionRequest) []PermissionOption {
 	}
 	options := make([]PermissionOption, 0, len(actions))
 	for _, action := range actions {
-		kind, name := optionKindFor(action)
+		kind, name := optionKindFor(action, req.PrefixApprovalEscalates)
 		if kind == "" {
 			continue // skip actions that have no clean ACP option (e.g. cancel)
 		}
@@ -41,18 +41,24 @@ func buildPermissionOptions(req agent.PermissionRequest) []PermissionOption {
 // optionKindFor maps a ZERO decision action to an ACP PermissionOptionKind and a
 // human label. Returns an empty kind for actions that ACP expresses through the
 // outcome rather than an option (cancel).
-func optionKindFor(action agent.PermissionDecisionAction) (kind, name string) {
+//
+// escalates reports that approving a command prefix will also run the command
+// outside the sandbox. The two prefix options say so in their label, since the
+// label is all an ACP client shows and the option id carries no room for it. An
+// editor user is deciding on exactly the same terms as a terminal user, so the
+// disclosure cannot be TUI-only.
+func optionKindFor(action agent.PermissionDecisionAction, escalates bool) (kind, name string) {
 	switch action {
 	case agent.PermissionDecisionAllow, agent.PermissionDecisionAllowStrict:
 		return PermAllowOnce, "Allow"
 	case agent.PermissionDecisionAllowForSession:
 		return PermAllowAlways, "Allow for this session"
 	case agent.PermissionDecisionAllowPrefix:
-		return PermAllowAlways, "Allow this command for the session"
+		return PermAllowAlways, withSandboxEscalationNote("Allow this command for the session", escalates)
 	case agent.PermissionDecisionAlwaysAllow:
 		return PermAllowAlways, "Always allow"
 	case agent.PermissionDecisionAlwaysAllowPrefix:
-		return PermAllowAlways, "Always allow this command"
+		return PermAllowAlways, withSandboxEscalationNote("Always allow this command", escalates)
 	case agent.PermissionDecisionDeny:
 		return PermRejectOnce, "Reject"
 	case agent.PermissionDecisionCancel:
@@ -123,3 +129,13 @@ func rawInputBytes(data []byte) json.RawMessage {
 	}
 	return json.RawMessage(data)
 }
+
+// withSandboxEscalationNote appends the escalation disclosure to a prefix
+// option's label. Kept parallel to the TUI's wording so the same consequence is
+// not described two different ways depending on which client the user runs.
+func withSandboxEscalationNote(name string, escalates bool) string {
+	if !escalates {
+		return name
+	}
+	return name + " (runs outside the sandbox)"
+}

internal/acp/permission_escalation_test.go

@@ -0,0 +1,68 @@
+package acp
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/Gitlawb/zero/internal/agent"
+)
+
+func escalationRequest(escalates bool) agent.PermissionRequest {
+	return agent.PermissionRequest{
+		ToolName: "bash",
+		AvailableDecisions: []agent.PermissionDecisionAction{
+			agent.PermissionDecisionAllow,
+			agent.PermissionDecisionAllowPrefix,
+			agent.PermissionDecisionAlwaysAllowPrefix,
+			agent.PermissionDecisionDeny,
+		},
+		PrefixApprovalEscalates: escalates,
+	}
+}
+
+// An ACP client renders only Name, so if the escalation is not in the label the
+// editor user approves it blind. They face exactly the outcome a terminal user
+// faces, so the disclosure has to reach both clients or it is not a fix.
+func TestACPPrefixOptionsDiscloseLeavingTheSandbox(t *testing.T) {
+	found := 0
+	for _, option := range buildPermissionOptions(escalationRequest(true)) {
+		action := agent.PermissionDecisionAction(option.OptionID)
+		if action != agent.PermissionDecisionAllowPrefix && action != agent.PermissionDecisionAlwaysAllowPrefix {
+			if strings.Contains(option.Name, "sandbox") {
+				t.Errorf("option %q carries the disclosure but does not escalate", option.Name)
+			}
+			continue
+		}
+		found++
+		if !strings.Contains(option.Name, "outside the sandbox") {
+			t.Errorf("prefix option %q does not say the command leaves the sandbox", option.Name)
+		}
+	}
+	if found != 2 {
+		t.Fatalf("expected both prefix options, saw %d", found)
+	}
+}
+
+func TestACPPrefixOptionsStaySilentWithoutEscalation(t *testing.T) {
+	for _, option := range buildPermissionOptions(escalationRequest(false)) {
+		if strings.Contains(option.Name, "sandbox") {
+			t.Errorf("option %q warns about the sandbox when approving would not leave it", option.Name)
+		}
+	}
+}
+
+// The disclosure must live in the label only. The option id is the decision
+// action round-tripped verbatim, and decisionFromOutcome matches it against
+// what was offered, so decorating it would fail every prefix approval closed.
+func TestACPDisclosureDoesNotDisturbTheOptionIDRoundTrip(t *testing.T) {
+	request := escalationRequest(true)
+	for _, option := range buildPermissionOptions(request) {
+		decision := decisionFromOutcome(
+			RequestPermissionOutcome{Outcome: OutcomeSelected, OptionID: option.OptionID},
+			request.AvailableDecisions,
+		)
+		if string(decision.Action) != option.OptionID {
+			t.Errorf("option id %q round-tripped to %q (%s)", option.OptionID, decision.Action, decision.Reason)
+		}
+	}
+}

internal/agent/loop.go

@@ -2718,9 +2718,36 @@ func permissionRequestFromEvent(event PermissionEvent, args map[string]any, opti
 		Grant:              event.Grant,
 		CommandPrefix:      append([]string(nil), event.CommandPrefix...),
 		AvailableDecisions: availablePermissionDecisions(event, args, options),
+		// Computed from the SAME conditions shellExecutionArgsForApproval uses,
+		// so the prompt cannot claim an escalation that will not happen or stay
+		// silent about one that will. Keeping the two in step matters more than
+		// the wording: a label that overstates gets ignored, and one that
+		// understates is the bug being fixed.
+		PrefixApprovalEscalates: shellPrefixApprovalEscalates(event.ToolName, args, options),
 	}
 }
 
+// shellPrefixApprovalEscalates reports whether approving a command prefix would
+// also take this command out of the sandbox.
+//
+// Deliberately mirrors shellExecutionArgsForApproval's guards rather than
+// re-deriving them: same tool test, same sandbox availability test, and the same
+// two opt-outs for a call that already asked for additional permissions or
+// escalation. Those already carry their own disclosure, so labelling them again
+// would be noise.
+func shellPrefixApprovalEscalates(toolName string, args map[string]any, options Options) bool {
+	if !isShellCommandTool(toolName) {
+		return false
+	}
+	if options.Sandbox == nil || !options.Sandbox.UnsandboxedExecutionAllowed() {
+		return false
+	}
+	if shellCommandAdditionalPermissionsRequested(args) || shellCommandRequiresEscalated(args) {
+		return false
+	}
+	return true
+}
+
 func availablePermissionDecisions(event PermissionEvent, args map[string]any, options Options) []PermissionDecisionAction {
 	if event.Action != PermissionActionPrompt {
 		return nil

internal/agent/prefix_escalation_disclosure_test.go

@@ -0,0 +1,118 @@
+package agent
+
+import (
+	"path/filepath"
+	"testing"
+
+	"github.com/Gitlawb/zero/internal/sandbox"
+	"github.com/Gitlawb/zero/internal/tools"
+)
+
+// escalatingEngine allows unsandboxed escalation: no denied reads, so
+// UnsandboxedExecutionAllowed is true and a prefix approval would rewrite the
+// call to require_escalated.
+func escalatingEngine(t *testing.T) *sandbox.Engine {
+	t.Helper()
+	policy := sandbox.DefaultPolicy()
+	policy.DenyRead = nil
+	return sandbox.NewEngine(sandbox.EngineOptions{WorkspaceRoot: t.TempDir(), Policy: policy})
+}
+
+// nonEscalatingEngine has a denied read, which is exactly the condition under
+// which escalation is refused, so no disclosure should be made.
+func nonEscalatingEngine(t *testing.T) *sandbox.Engine {
+	t.Helper()
+	root := t.TempDir()
+	policy := sandbox.DefaultPolicy()
+	policy.DenyRead = []string{filepath.Join(root, "secret.txt")}
+	return sandbox.NewEngine(sandbox.EngineOptions{WorkspaceRoot: root, Policy: policy})
+}
+
+// THE POINT OF THE FILE. The prompt's disclosure and the args rewrite must
+// agree on every input, because the defect being fixed is precisely that the
+// two disagreed: the rewrite escalated out of the sandbox while the prompt said
+// only "allow command prefix for session".
+//
+// Asserting agreement rather than asserting each side's expected value is what
+// makes this hold up. If someone later widens or narrows the rewrite's guards
+// and forgets the flag, the two diverge here and this fails, which a pair of
+// independent expected-value tests would not catch.
+func TestPrefixEscalationDisclosureMatchesTheArgsRewrite(t *testing.T) {
+	escalating := Options{Sandbox: escalatingEngine(t)}
+	denied := Options{Sandbox: nonEscalatingEngine(t)}
+
+	cases := []struct {
+		name     string
+		toolName string
+		args     map[string]any
+		options  Options
+	}{
+		{"plain bash command", "bash", map[string]any{"command": "go test ./..."}, escalating},
+		{"plain exec_command", "exec_command", map[string]any{"cmd": "go build ./..."}, escalating},
+		{"not a shell tool", "read_file", map[string]any{"path": "go.mod"}, escalating},
+		{"no sandbox configured", "bash", map[string]any{"command": "go test ./..."}, Options{}},
+		{"escalation refused by denied reads", "bash", map[string]any{"command": "go test ./..."}, denied},
+		{
+			"call already asks for escalation",
+			"bash",
+			map[string]any{"command": "go test ./...", "sandbox_permissions": string(tools.SandboxPermissionsRequireEscalated)},
+			escalating,
+		},
+		{
+			"call already asks for additional permissions",
+			"bash",
+			map[string]any{"command": "go test ./...", "sandbox_permissions": string(tools.SandboxPermissionsWithAdditionalPermissions)},
+			escalating,
+		},
+		// An unrecognized value is NOT an opt-out: the rewrite overwrites it, so
+		// the disclosure has to fire. Included because the obvious reading of
+		// the guards says otherwise, and a case asserting the wrong thing here
+		// would have passed silently.
+		{
+			"unrecognized sandbox_permissions value",
+			"bash",
+			map[string]any{"command": "go test ./...", "sandbox_permissions": "all"},
+			escalating,
+		},
+		{"empty args", "bash", map[string]any{}, escalating},
+		{"nil args", "bash", nil, escalating},
+	}
+
+	for _, testCase := range cases {
+		t.Run(testCase.name, func(t *testing.T) {
+			disclosed := shellPrefixApprovalEscalates(testCase.toolName, testCase.args, testCase.options)
+
+			// What the user's approval would actually be turned into.
+			rewritten := shellExecutionArgsForApproval(testCase.toolName, testCase.args, PermissionDecisionAllowPrefix, testCase.options)
+			escalates := shellCommandRequiresEscalated(rewritten) && !shellCommandRequiresEscalated(testCase.args)
+
+			if disclosed != escalates {
+				t.Fatalf("prompt discloses escalation=%v but approving actually escalates=%v; the prompt and the rewrite disagree, which is the consent gap this guards", disclosed, escalates)
+			}
+		})
+	}
+}
+
+// The two prefix decisions are the only ones that escalate, so a disclosure
+// attached to a request offering neither would be a false alarm. Checked
+// against the same predicate the rewrite consults.
+func TestOnlyPrefixDecisionsEscalate(t *testing.T) {
+	escalating := map[PermissionDecisionAction]bool{
+		PermissionDecisionAllowPrefix:       true,
+		PermissionDecisionAlwaysAllowPrefix: true,
+	}
+	for _, action := range []PermissionDecisionAction{
+		PermissionDecisionAllow,
+		PermissionDecisionAllowStrict,
+		PermissionDecisionAllowForSession,
+		PermissionDecisionAllowPrefix,
+		PermissionDecisionAlwaysAllowPrefix,
+		PermissionDecisionAlwaysAllow,
+		PermissionDecisionDeny,
+		PermissionDecisionCancel,
+	} {
+		if got := shellPrefixApprovalBypassesSandbox(action); got != escalating[action] {
+			t.Errorf("decision %q bypasses sandbox=%v, want %v", action, got, escalating[action])
+		}
+	}
+}

internal/agent/types.go

@@ -176,6 +176,22 @@ type PermissionRequest struct {
 	Grant              *sandbox.Grant             `json:"grant,omitempty"`
 	CommandPrefix      []string                   `json:"commandPrefix,omitempty"`
 	AvailableDecisions []PermissionDecisionAction `json:"availableDecisions,omitempty"`
+	// PrefixApprovalEscalates reports that approving a command prefix will also
+	// run the command OUTSIDE the sandbox, not merely stop asking about it.
+	//
+	// It exists because that consequence was real but invisible. Approving a
+	// prefix rewrites the call to sandbox_permissions: require_escalated, which
+	// resolves to a nil engine and genuinely unsandboxed execution, and the
+	// engine's own escalation prompt is then satisfied by the approval just
+	// given for the sandboxed form. So the operator authorized one thing and got
+	// a wider one, having been shown only "allow command prefix for session".
+	//
+	// The escalation itself is deliberate and guarded: proposedCommandPrefix
+	// refuses to offer a prefix while any other segment of the command is not
+	// known-safe, precisely so an unreviewed segment cannot ride out of the
+	// sandbox on it. What was missing was telling the person deciding, so this
+	// surfaces it rather than removing it.
+	PrefixApprovalEscalates bool `json:"prefixApprovalEscalates,omitempty"`
 }
 
 type PermissionDecision struct {

internal/tui/permission_prompt.go

@@ -43,9 +43,9 @@ func permissionOptions(request agent.PermissionRequest) []permissionOption {
 		case agent.PermissionDecisionAllowForSession:
 			options = append(options, permissionOption{label: "allow for session", hotkey: "s", choice: permissionDecisionAllowForSession})
 		case agent.PermissionDecisionAllowPrefix:
-			options = append(options, permissionOption{label: "allow command prefix for session", hotkey: "p", choice: permissionDecisionAllowPrefix})
+			options = append(options, permissionOption{label: prefixApprovalLabel("allow command prefix for session", request), hotkey: "p", choice: permissionDecisionAllowPrefix})
 		case agent.PermissionDecisionAlwaysAllowPrefix:
-			options = append(options, permissionOption{label: "always allow command prefix", hotkey: "y", choice: permissionDecisionAlwaysAllowPrefix})
+			options = append(options, permissionOption{label: prefixApprovalLabel("always allow command prefix", request), hotkey: "y", choice: permissionDecisionAlwaysAllowPrefix})
 		case agent.PermissionDecisionAlwaysAllow:
 			options = append(options, permissionOption{label: "always", hotkey: "y", choice: permissionDecisionAlwaysAllow})
 		case agent.PermissionDecisionDeny:
@@ -155,3 +155,21 @@ func (m model) cancelPermissionTyping() (tea.Model, tea.Cmd) {
 	m.pendingPermission.savedDraft = ""
 	return m, nil
 }
+
+// prefixApprovalLabel spells out that approving a prefix also takes the command
+// out of the sandbox.
+//
+// Approving a prefix rewrites the call to require_escalated, which resolves to
+// unsandboxed execution, and the engine's escalation prompt is then satisfied by
+// the approval just given for the sandboxed form. The operator was shown only
+// "allow command prefix for session" and got something wider, which is a consent
+// gap rather than a bug in the escalation itself.
+//
+// Only appended when it is true. The backend computes that from the same guards
+// the rewrite uses, so a prompt that says this always means it.
+func prefixApprovalLabel(base string, request agent.PermissionRequest) string {
+	if !request.PrefixApprovalEscalates {
+		return base
+	}
+	return base + " (runs outside the sandbox)"
+}

internal/tui/permission_prompt_escalation_test.go

@@ -0,0 +1,70 @@
+package tui
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/Gitlawb/zero/internal/agent"
+)
+
+func prefixOptionLabels(request agent.PermissionRequest) []string {
+	labels := []string{}
+	for _, option := range permissionOptions(request) {
+		if option.choice == permissionDecisionAllowPrefix || option.choice == permissionDecisionAlwaysAllowPrefix {
+			labels = append(labels, option.label)
+		}
+	}
+	return labels
+}
+
+func prefixRequest(escalates bool) agent.PermissionRequest {
+	return agent.PermissionRequest{
+		ToolName: "bash",
+		AvailableDecisions: []agent.PermissionDecisionAction{
+			agent.PermissionDecisionAllow,
+			agent.PermissionDecisionAllowPrefix,
+			agent.PermissionDecisionAlwaysAllowPrefix,
+			agent.PermissionDecisionDeny,
+		},
+		PrefixApprovalEscalates: escalates,
+	}
+}
+
+// Approving a prefix also runs the command outside the sandbox, and the label
+// is the only place the person deciding could learn that. Both prefix options
+// escalate, so both must say so; covering only one would leave the other as a
+// silent path to the same outcome.
+func TestPrefixOptionsDiscloseLeavingTheSandbox(t *testing.T) {
+	labels := prefixOptionLabels(prefixRequest(true))
+	if len(labels) != 2 {
+		t.Fatalf("expected both prefix options, got %#v", labels)
+	}
+	for _, label := range labels {
+		if !strings.Contains(label, "outside the sandbox") {
+			t.Errorf("prefix option %q does not say the command leaves the sandbox, so approving it is uninformed consent", label)
+		}
+	}
+}
+
+// The disclosure has to be conditional. When escalation will not happen, saying
+// it will is a false warning, and a prompt that cries wolf on every prefix is
+// one the user learns to ignore, which costs the disclosure its whole value.
+func TestPrefixOptionsStaySilentWhenNoEscalationHappens(t *testing.T) {
+	for _, label := range prefixOptionLabels(prefixRequest(false)) {
+		if strings.Contains(label, "sandbox") {
+			t.Errorf("prefix option %q warns about the sandbox when approving would not leave it", label)
+		}
+	}
+}
+
+// The non-prefix options do not escalate, so the flag must not bleed into them.
+func TestNonPrefixOptionsNeverCarryTheDisclosure(t *testing.T) {
+	for _, option := range permissionOptions(prefixRequest(true)) {
+		if option.choice == permissionDecisionAllowPrefix || option.choice == permissionDecisionAlwaysAllowPrefix {
+			continue
+		}
+		if strings.Contains(option.label, "sandbox") {
+			t.Errorf("option %q carries the prefix escalation disclosure but does not escalate", option.label)
+		}
+	}
+}