R-861 (a) A1 + (b) B2: the image ref goes to a root verb that checks it; the agent's in-guest tee grant is gone; felhom-op's pct lines are exact (09 §3 decision 165)

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

configs/felhom-agent.sudoers

@@ -111,15 +111,17 @@ Cmnd_Alias FELHOM_INTERMEDIARY = \
 #   docker inspect -f *         — container running/health/image (read-only; `*` spans the -f template
 #                                 + container across spaces, spike-confirmed)
 #   systemctl restart <fixed unit> — re-run the golden's bootstrap (the only state change)
-#   tee <FIXED image file>      — WRITE the ref; content is fed on STDIN (no shell, no interpolation),
-#                                 the agent strict-validates the ref (controllerImageRe) before the write.
+#   felhom-priv-apply controller-image <vmid> — WRITE the ref (R-861 (a) A1, `09` §3 decision 165): the ref goes on
+#                                 STDIN to the ROOT wrapper, which requires our registry + repository + an x.y.z tag
+#                                 and writes the guest file itself. The agent's own `tee` grant is GONE: before, a
+#                                 compromised agent could hand the guest's bootstrap ANY image (sudo cannot see stdin).
 # Validated GO: felhom.eu/documentation/audits/SPIKE-controllerswap-narrow-grants-2026-06-29.md.
 Cmnd_Alias FELHOM_CONTROLLERSWAP = \
   /usr/sbin/pct ^exec [0-9]+ -- cat /etc/felhom-controller-image$, \
   /usr/sbin/pct ^exec [0-9]+ -- docker image inspect gitea\.dooplex\.hu/admin/felhom-controller\:[0-9]+\.[0-9]+\.[0-9]+$, \
   /usr/sbin/pct ^exec [0-9]+ -- docker inspect -f .+ (felhom-controller|cloudflared)$, \
   /usr/sbin/pct ^exec [0-9]+ -- systemctl restart felhom-controller-bootstrap\.service$, \
-  /usr/sbin/pct ^exec [0-9]+ -- tee /etc/felhom-controller-image$
+  /usr/local/sbin/felhom-priv-apply ^controller-image [0-9]+$
 
 # Stale-lock recovery (F2-b, v0.49.0). A host reboot DURING a vzdump backup leaves the guest with a
 # `snapshot-delete`/`backup` lock + `onboot:1` then can't start it → the customer box stays DOWN. The

configs/felhom-op.sudoers

@@ -16,8 +16,10 @@ Cmnd_Alias FELHOM_OP_REPAIR = \
   /usr/bin/systemctl reset-failed felhom-sshd, \
   /usr/bin/systemctl restart felhom-sshd, \
   /usr/sbin/pct list, \
-  /usr/sbin/pct start [0-9]*, \
-  /usr/sbin/pct stop [0-9]*, \
-  /usr/sbin/pct unlock [0-9]*
+  /usr/sbin/pct ^start [0-9]+$, \
+  /usr/sbin/pct ^stop [0-9]+$, \
+  /usr/sbin/pct ^unlock [0-9]+$
 
+# R-861 (b) B2 (`09` §3 decision 165, hygiene): one numeric vmid per pct verb, anchored — the old glob `[0-9]*` also
+# matched spaces, so `pct stop 9201 --skiplock 1` passed. Pinned by TestFelhomOpSudoersPctIsExact.
 felhom-op ALL=(root) NOPASSWD: FELHOM_OP_REPAIR

configs/felhom-priv-apply

@@ -17,6 +17,8 @@ Verbs (each one sudoers line, exact-match pattern):
   wg                       /var/lib/felhom-agent/wg/wg-felhom.conf -> /etc/wireguard/wg-felhom.conf (0600)
   sshd-config              /var/lib/felhom-agent/felhom-sshd/sshd_config -> /etc/felhom-sshd/sshd_config
   sshd-key                 /var/lib/felhom-agent/felhom-sshd/authorized_keys.felhom-op -> /etc/felhom-sshd/authorized_keys/felhom-op
+  controller-image <vmid>  the ref on STDIN -> /etc/felhom-controller-image INSIDE guest <vmid> (R-861 (a) A1): only
+                           our registry + our repository + an x.y.z tag; the agent no longer has a `tee` grant
   --self-check             prints "felhom-priv-apply ok verbs=..." (the bundle's self-check)
 
 Exit codes: 0 installed (or already identical), 2 usage, 3 refused (content or source), 4 install failed.
@@ -39,7 +41,14 @@ WG_SRC, WG_DEST = STATE + "/wg/wg-felhom.conf", "/etc/wireguard/wg-felhom.conf"
 SSHD_SRC, SSHD_DEST = STATE + "/felhom-sshd/sshd_config", "/etc/felhom-sshd/sshd_config"
 KEY_SRC, KEY_DEST = STATE + "/felhom-sshd/authorized_keys.felhom-op", "/etc/felhom-sshd/authorized_keys/felhom-op"
 MAX_BYTES = 64 * 1024
-VERBS = ("unit", "dnsmasq", "wg", "sshd-config", "sshd-key")
+VERBS = ("unit", "dnsmasq", "wg", "sshd-config", "sshd-key", "controller-image")
+# R-861 (a) A1 (`09` §3 decision 165): the SAME pattern as the agent's controllerImageRe (internal/localapi/
+# controllerswap.go) — a compromised agent cannot hand the guest's bootstrap any other image. Pinned by
+# configs/test_felhom_priv_apply.py ControllerImage.
+CONTROLLER_IMAGE_RE = re.compile(r"^gitea\.dooplex\.hu/admin/felhom-controller:[0-9]+\.[0-9]+\.[0-9]+$")
+CONTROLLER_IMAGE_FILE = "/etc/felhom-controller-image"
+CONTROLLER_IMAGE_MAX = 256
+VMID_RE = re.compile(r"^[0-9]{1,9}$")
 
 UNIT_NAME_RE = re.compile(r"^mnt-[A-Za-z0-9_.\\-]+\.(mount|automount)$")
 DNSMASQ_TMP_RE = re.compile(r"^/tmp/felhom-resolver-[0-9]+\.conf$")
@@ -123,6 +132,16 @@ class Host:
                 pass
             raise
 
+    def read_stdin(self, limit):
+        return sys.stdin.buffer.read(limit + 1)
+
+    def write_guest_image(self, vmid, data):
+        """As root: `pct exec <vmid> -- tee <the fixed file>` with the checked ref on stdin (no shell)."""
+        r = subprocess.run(["/usr/sbin/pct", "exec", str(vmid), "--", "tee", CONTROLLER_IMAGE_FILE],
+                           input=data, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE, timeout=60)
+        if r.returncode != 0:
+            raise OSError(f"pct exec {vmid} tee exited {r.returncode}: {r.stderr.decode(errors='replace').strip()[:200]}")
+
     def log(self, line):
         print(line, file=sys.stderr)
         try:
@@ -377,6 +396,34 @@ def plan(argv):
     raise Refused("A1", f"wrong arguments for {v}")
 
 
+def controller_image(rest, host):
+    """R-861 (a) A1: read the ref on stdin, check it, write it INSIDE the guest as root."""
+    try:
+        if len(rest) != 1 or not VMID_RE.match(rest[0]):
+            raise Refused("A1", "usage: felhom-priv-apply controller-image <vmid>  (the ref on stdin)")
+        raw = host.read_stdin(CONTROLLER_IMAGE_MAX)
+        if len(raw) > CONTROLLER_IMAGE_MAX:
+            raise Refused("I1", f"the image ref is longer than {CONTROLLER_IMAGE_MAX} bytes")
+        try:
+            text = raw.decode("ascii")
+        except UnicodeDecodeError:
+            raise Refused("I1", "the image ref is not ASCII")
+        ref = text[:-1] if text.endswith("\n") else text
+        if not CONTROLLER_IMAGE_RE.match(ref) or "\n" in ref:
+            raise Refused("I1", "the image ref is not gitea.dooplex.hu/admin/felhom-controller:<x.y.z>")
+    except Refused as e:
+        host.log(f"felhom-priv-apply: REFUSED [{e.rule}] controller-image {' '.join(rest)[:40]}: {e.reason}")
+        return 2 if e.rule == "A1" else 3
+    vmid = int(rest[0])
+    try:
+        host.write_guest_image(vmid, (ref + "\n").encode())
+    except (OSError, subprocess.SubprocessError) as e:
+        host.log(f"felhom-priv-apply: FAILED controller-image {vmid}: {e}")
+        return 4
+    host.log(f"felhom-priv-apply: WROTE controller-image {vmid} {ref}")
+    return 0
+
+
 def main(argv, host=None):
     host = host or Host()
     if argv == ["--self-check"]:
@@ -396,6 +443,8 @@ def main(argv, host=None):
             return 3
         print("OK")
         return 0
+    if argv and argv[0] == "controller-image":
+        return controller_image(argv[1:], host)
     try:
         verb, src, dest, mode, checker = plan(argv)
         data = host.read_source(src)

configs/test_felhom_priv_apply.py

@@ -56,6 +56,18 @@ class FakeHost:
     def log(self, line):
         self.logs.append(line)
 
+    # controller-image (R-861 (a) A1): the ref arrives on stdin and is written INSIDE the guest by root.
+    stdin = b""
+    guest_writes = None
+
+    def read_stdin(self, limit):
+        return self.stdin[:limit + 1]
+
+    def write_guest_image(self, vmid, data):
+        if self.guest_writes is None:
+            self.guest_writes = []
+        self.guest_writes.append((vmid, data))
+
 
 LOCAL_UNIT = """# Managed by felhom-agent — do not edit by hand.
 [Unit]
@@ -316,5 +328,53 @@ class Refuses(unittest.TestCase):
         self.refused(h, ["wg", "/etc/shadow"], "A1")
 
 
+class ControllerImage(unittest.TestCase):
+    """R-861 (a) A1 (`09` §3 decision 165): the agent can no longer `tee` any image ref into the guest. The root verb
+    reads the ref on stdin, requires our registry + our repository + an x.y.z tag, and writes the guest file itself.
+    RED-PROOF: on the pre-A1 wrapper `controller-image` is not a verb (A1 usage, rc 2) — the accepted case fails."""
+
+    def go(self, ref, *argv):
+        h = FakeHost()
+        h.stdin = ref.encode() if isinstance(ref, str) else ref
+        return h, run(h, *(argv or ("controller-image", "9201")))
+
+    def test_our_controller_ref_is_written_in_the_guest(self):
+        h, rc = self.go("gitea.dooplex.hu/admin/felhom-controller:0.301.0\n")
+        self.assertEqual(rc, 0, h.logs)
+        self.assertEqual(h.guest_writes, [(9201, b"gitea.dooplex.hu/admin/felhom-controller:0.301.0\n")])
+
+    def test_a_foreign_image_is_refused(self):
+        for ref in ("docker.io/library/alpine:latest\n", "alpine\n",
+                    "gitea.dooplex.hu/admin/felhom-controller:latest\n",
+                    "gitea.dooplex.hu/admin/other:0.1.0\n",
+                    "evil.example/admin/felhom-controller:0.301.0\n",
+                    "gitea.dooplex.hu/admin/felhom-controller:0.301.0\nalpine\n",
+                    "gitea.dooplex.hu/admin/felhom-controller:0.301.0 x\n",
+                    "", "\n"):
+            h, rc = self.go(ref)
+            self.assertEqual(rc, 3, f"{ref!r} was accepted")
+            self.assertFalse(h.guest_writes, f"{ref!r} wrote the guest file")
+            self.assertTrue(any("[I1]" in l for l in h.logs), h.logs)
+
+    def test_oversize_stdin_is_refused(self):
+        h, rc = self.go("gitea.dooplex.hu/admin/felhom-controller:0.301.0" + " " * 300)
+        self.assertEqual(rc, 3)
+        self.assertFalse(h.guest_writes)
+
+    def test_vmid_must_be_numeric(self):
+        for argv in (("controller-image", "9201;id"), ("controller-image", "-1"), ("controller-image",),
+                     ("controller-image", "9201", "9202")):
+            h, rc = self.go("gitea.dooplex.hu/admin/felhom-controller:0.301.0\n", *argv)
+            self.assertIn(rc, (2, 3), argv)
+            self.assertFalse(h.guest_writes, argv)
+
+    def test_self_check_names_the_verb(self):
+        import io, contextlib
+        buf = io.StringIO()
+        with contextlib.redirect_stdout(buf):
+            pa.main(["--self-check"])
+        self.assertIn("controller-image", buf.getvalue())
+
+
 if __name__ == "__main__":
     unittest.main(verbosity=2)