R-861: narrow the agent's root grants — exact sudo patterns, felhom-priv-apply content checker, fixed hook/parent files in the bundle, signed self-update verified as root, escrow root reads pinned

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS

internal/localapi/intermediary.go

@@ -121,32 +121,33 @@ func (b *GuestBinder) EnsureSharedParent(ctx context.Context) error {
 	// only the script (the unit was unchanged), so the earlier unit-only gate never redeployed it —
 	// leaving hosts running the pre-fix script (no make-private), whose self-bind stays in root's shared
 	// peer group and DOUBLES every drive bind. Comparing both files closes that deploy gap.
-	if sharedParentInstallStale(sharedParentUnitPath, sharedParentScriptPath) {
-		if ierr := b.installSharedParentUnit(ctx); ierr != nil {
-			b.logger.Warn("shared-parent: boot-persistence (re)install failed (live setup OK; survives until host reboot)", "err", ierr)
-		}
+	if err := b.ensureSharedParentBoot(ctx, sharedParentUnitPath, sharedParentScriptPath, sharedParentWantsLink); err != nil {
+		b.logger.Warn("shared-parent: boot persistence not enabled (live setup OK; survives until host reboot)", "err", err)
 	}
 	return nil
 }
 
-// stageTemp writes content to a fresh random-named temp file (os.CreateTemp pattern — `*` is replaced
-// by a random string) and returns its path. Caller removes it after the privileged `install`.
-func stageTemp(pattern, content string) (string, error) {
-	f, err := os.CreateTemp("", pattern)
-	if err != nil {
-		return "", err
+// sharedParentWantsLink exists once `systemctl enable felhom-shared-parent.service` ran (WantedBy=pve-guests.service).
+const sharedParentWantsLink = "/etc/systemd/system/pve-guests.service.wants/felhom-shared-parent.service"
+
+// ensureSharedParentBoot (R-861, agent v0.146.0) — the boot script and its unit are ROOT-OWNED FIXED files that arrive
+// with the signed config bundle (configs/felhom-shared-parent.{sh,service}, byte-identical to the constants above,
+// pinned by TestSharedParentFilesEqualTheBundle). The agent NEVER installs them any more: until v0.146.0 it installed
+// them from /tmp, and a script a root unit runs at boot was a root shell for a compromised agent. Here it only checks
+// them, and enables the unit (a fixed sudoers line) when the bundle has put it in place but nothing has enabled it — a
+// fresh install. Missing or different files: one warning, nothing run (the next bundle brings them).
+func (b *GuestBinder) ensureSharedParentBoot(ctx context.Context, unitPath, scriptPath, wantsLink string) error {
+	if sharedParentInstallStale(unitPath, scriptPath) {
+		return fmt.Errorf("%s or %s is missing or differs from this agent's — it arrives with the signed config bundle (agent_config_update); the agent does not install it (R-861)", scriptPath, unitPath)
 	}
-	name := f.Name()
-	if _, err := f.WriteString(content); err != nil {
-		f.Close()
-		os.Remove(name)
-		return "", err
+	if _, err := os.Lstat(wantsLink); err == nil {
+		return nil
 	}
-	if err := f.Close(); err != nil {
-		os.Remove(name)
-		return "", err
+	if err := b.run(ctx, "systemctl", "enable", "felhom-shared-parent.service"); err != nil {
+		return fmt.Errorf("enable unit: %w", err)
 	}
-	return name, nil
+	b.logger.Info("shared-parent: boot-persistence unit enabled (files from the config bundle)")
+	return nil
 }
 
 // sharedParentInstallStale reports whether the on-disk boot script OR unit is missing or differs from
@@ -162,37 +163,6 @@ func sharedParentInstallStale(unitPath, scriptPath string) bool {
 	return false
 }
 
-// installSharedParentUnit writes the script + unit (from agent-written temps) and enables the unit so the
-// shared parent is re-established on every host boot before pve-guests. Idempotent. The temps are
-// RANDOM-named os.CreateTemp files (audit B1): a fixed, predictable /tmp name could be pre-created by
-// another local user and rewritten between our write and root's install (TOCTOU into a root-executed
-// boot script). The final modes come from `install -m`, so the 0600 temps are fine.
-func (b *GuestBinder) installSharedParentUnit(ctx context.Context) error {
-	tmpScript, err := stageTemp("felhom-shared-parent-*.sh", sharedParentScript)
-	if err != nil {
-		return fmt.Errorf("write temp script: %w", err)
-	}
-	defer os.Remove(tmpScript)
-	if err := b.run(ctx, "install", "-m", "0755", "--", tmpScript, sharedParentScriptPath); err != nil {
-		return fmt.Errorf("install script: %w", err)
-	}
-	tmpUnit, err := stageTemp("felhom-shared-parent-*.service", sharedParentUnit)
-	if err != nil {
-		return fmt.Errorf("write temp unit: %w", err)
-	}
-	defer os.Remove(tmpUnit)
-	if err := b.run(ctx, "install", "-m", "0644", "--", tmpUnit, sharedParentUnitPath); err != nil {
-		return fmt.Errorf("install unit: %w", err)
-	}
-	if err := b.run(ctx, "systemctl", "daemon-reload"); err != nil {
-		return fmt.Errorf("daemon-reload: %w", err)
-	}
-	if err := b.run(ctx, "systemctl", "enable", "felhom-shared-parent.service"); err != nil {
-		return fmt.Errorf("enable unit: %w", err)
-	}
-	return nil
-}
-
 // AttachDrive binds a drive's felhom-data namespace under the stable parent so it appears live in the
 // guest at the returned stable path (via propagation — no pct, no reboot). `where` is the drive's RAW
 // host PVE mount (/mnt/<name>); only `<where>/felhom-data` crosses into the guest (confinement). The