feat(setup-host): refuse a claimed subnet, and BOX_SUBNET to move off one (#80)

Run inside a box, setup-host built a nested boxnet claiming the exact
subnet and gateway of the guest's own uplink: the guest then held
10.88.0.1 as a LOCAL address while its default route pointed at 10.88.0.1
as its GATEWAY, carried two connected routes for the subnet, and suffered
intermittent, self-recovering egress blackouts (~24-36 s, roughly hourly)
that no host-side check could attribute. The flagship use case funnels
agents toward exactly this — working on box, in a box — so the guard, not
the operator, has to catch it.

setup-host now scans the target subnet BEFORE any mutation: the default
route's gateway inside it (the smoking gun — that is this machine's own
uplink), or any non-boxnet interface holding an address in it, refuses
with the way out named (BOX_SUBNET). A prior boxnet owning the subnet is
the one claimant that is NOT a collision — the legitimate re-run — and an
existing bridge on a DIFFERENT subnet refuses too: setup-host converges a
bridge, it never re-addresses one under live leases.

BOX_SUBNET=<a.b.c.0/24> (validated at the gate, alongside BOX_DNS) moves
the whole stack from one place:
  · the bridge address derives (ipv4.address=<gw>/24)
  · the ACL's gateway carve-out derives — and the ruleset is now converged
    via 'network acl edit', not created once: the #80 escape hatch (moving
    the bridge) left the old /32 behind, stranding box DNS inside the
    10.0.0.0/8 drop, which presents as a dead resolver, never as a stale
    ACL
  · box-firewall reads the gateway off the live bridge ('|| true' because
    under pipefail an absent bridge would kill the script instead of
    answering "no bridge yet")
  · the drill, multiuser rehearsal and migrate-host probes derive the
    prefix from 'incus network get boxnet ipv4.address' instead of
    hardcoding 10.88 — a BOX_SUBNET host must not fail its own rehearsals

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
dan-claude-bot 2026-07-18 19:46:58 +00:00
parent 26a218f29c
commit b429f5b65c
5 changed files with 157 additions and 33 deletions

View file

@ -94,14 +94,17 @@ in_box() {
# · and the interface is NOT called eth0. The PROFILE names the device eth0,
# but inside a VM guest predictable naming renames it enp5s0. Six runs of
# A3 "not probed" were this, not the network.
# So: read it from inside the box, and select by SUBNET (10.88.x, what boxnet
# hands out) rather than by interface name — docker0 (172.17.x) is the decoy,
# and the NIC's name is the guest's business, not ours.
# So: read it from inside the box, and select by SUBNET (what boxnet hands
# out — read off the network, never hardcoded: BOX_SUBNET moves it, #80)
# rather than by interface name — docker0 (172.17.x) is the decoy, and the
# NIC's name is the guest's business, not ours.
boxnet_gw() { incus network get boxnet ipv4.address 2>/dev/null | cut -d/ -f1; }
boxnet_ip() {
local b="$1" ip _i
local b="$1" ip _i pfx
pfx="$(boxnet_gw)"; pfx="${pfx%.*}."
for _i in $(seq 1 15); do
ip="$(in_box "$b" ip -4 -o addr show scope global \
| awk '{ for (i = 1; i < NF; i++) if ($i == "inet" && $(i+1) ~ /^10\.88\./) { split($(i+1), a, "/"); print a[1]; exit } }')"
| awk -v p="$pfx" '{ for (i = 1; i < NF; i++) if ($i == "inet" && index($(i+1), p) == 1) { split($(i+1), a, "/"); print a[1]; exit } }')"
[ -n "$ip" ] && { printf '%s\n' "$ip"; return 0; }
sleep 2
done
@ -693,10 +696,11 @@ fi
# nothing serves and read refused-vs-dropped — refused would mean the box's
# packet reached the host's stack, which is the thing the firewall must prevent.
# (No background listener: one less process to leak, one less way to wedge.)
hv="$(box_probe archive http://10.88.0.1:8099)"
gw="$(boxnet_gw)"
hv="$(box_probe archive "http://$gw:8099")"
case "$hv" in
reachable|refused)
no "THE BOX'S PACKETS REACH THE HOST on 10.88.0.1:8099 [$hv] — the firewall rules are not holding"
no "THE BOX'S PACKETS REACH THE HOST on $gw:8099 [$hv] — the firewall rules are not holding"
aud "A2 box→host: FAIL — $hv (the packet reached the host's stack)" ;;
dropped)
ok "box → host is blocked (no path to the machine's sockets)"
@ -747,7 +751,7 @@ elif [ -n "$PEER_IP" ]; then
fi
else
no "could not read peer's boxnet address — the sibling probe never ran"
aud "A3 sibling: NOT PROBED (no 10.88.x address on peer)"
aud "A3 sibling: NOT PROBED (no boxnet address on peer)"
fi
# C5 — DNS enumeration (#15 A4). Now a CONTRACT, not an observation: setup-host
@ -936,7 +940,7 @@ else
|| no "migrate: legacy box is NOT on box-net"
lip="$(boxnet_ip legacybox)"
[ -n "$lip" ] && ok "migrate: legacy box got a boxnet address ($lip) — network move landed" \
|| no "migrate: legacy box has no 10.88 address — the move did not take"
|| no "migrate: legacy box has no boxnet address — the move did not take"
in_box legacybox getent hosts deb.debian.org >/dev/null 2>&1 \
&& ok "migrate: re-homed box resolves + reaches the internet on its new leg" \
|| no "migrate: re-homed box cannot resolve on boxnet"

View file

@ -105,6 +105,11 @@ probe_up() { # probe_up <user> <box> <url>
echo "$r"
}
# The hardened network's gateway and prefix, read off the network — never
# hardcoded, because BOX_SUBNET moves the whole subnet now (#80).
boxnet_gw() { incus network get boxnet ipv4.address 2>/dev/null | cut -d/ -f1; }
boxnet_pfx() { local gw; gw="$(boxnet_gw)"; printf '%s.' "${gw%.*}"; }
cleanup() {
[ "$KEEP" = 1 ] && { echo "(--keep: users and boxes left for inspection)"; return; }
echo
@ -194,8 +199,8 @@ fi
rm -f "$mintlog"
as_u "$U1" box list 2>/dev/null | grep -q '^mine ' && ok "(b) box list shows mine" || no "(b) box list does not show mine"
as_u "$U1" box exec mine -- true >/dev/null 2>&1 && ok "(b) box exec mine -- true" || no "(b) box exec failed"
as_u "$U1" box info mine 2>/dev/null | grep -q '10\.88\.' \
&& ok "(g) box info shows a boxnet (10.88.x) address — placed on the hardened network" \
as_u "$U1" box info mine 2>/dev/null | grep -qF "$(boxnet_pfx)" \
&& ok "(g) box info shows a boxnet ($(boxnet_pfx)x) address — placed on the hardened network" \
|| no "(g) mine has no boxnet address in box info"
as_u "$U1" box snapshot mine s1 >/dev/null 2>&1 && ok "(b) box snapshot mine s1" || no "(b) snapshot refused"
as_u "$U1" box restore mine s1 >/dev/null 2>&1 && ok "(b) box restore mine s1 (the incus 6 'snapshot restore' spelling)" || no "(b) restore failed"
@ -224,14 +229,14 @@ phase "g. the isolation contract, measured from INSIDE the boxes"
ip1="$(incus --project "$p1" list mine --format csv --columns 4 2>/dev/null | tr -d '"' | sed 's/ (.*//' | head -n1)"
ip2="$(incus --project "$p2" list mine --format csv --columns 4 2>/dev/null | tr -d '"' | sed 's/ (.*//' | head -n1)"
inf "$U1's mine: ${ip1:-<no ip>} $U2's mine: ${ip2:-<no ip>}"
case "$ip1" in 10.88.*) ok "(g) $U1's box holds a boxnet lease" ;; *) no "(g) $U1's box is NOT on boxnet: '$ip1'" ;; esac
case "$ip1" in "$(boxnet_pfx)"*) ok "(g) $U1's box holds a boxnet lease" ;; *) no "(g) $U1's box is NOT on boxnet: '$ip1'" ;; esac
r="$(probe_up "$U1" mine https://1.1.1.1)"
[ "$r" = reachable ] && ok "(g) egress to the public internet works (curl 1.1.1.1: $r)" || no "(g) public egress broken: $r"
as_u "$U1" timeout -k 5 20 incus exec mine -- getent hosts deb.debian.org >/dev/null 2>&1 \
&& ok "(g) public DNS resolves (via the pinned resolver)" || no "(g) DNS broken inside the box"
r="$(probe_from "$U1" mine "http://10.88.0.1:22")"
r="$(probe_from "$U1" mine "http://$(boxnet_gw):22")"
[ "$r" = dropped ] && ok "(g) box → host is dropped (gateway :22: $r)" || no "(g) box can reach the HOST: $r"
r="$(probe_from "$U1" mine "http://192.168.0.1")"
[ "$r" = dropped ] && ok "(g) box → RFC1918 is dropped ($r)" || no "(g) box reaches private space: $r"

View file

@ -5,8 +5,16 @@
# Docker's DOCKER-USER rules are runtime-only and need re-applying).
set -euo pipefail
GW=10.88.0.1
NET=boxnet
# The gateway is read off the live bridge, not hardcoded: the subnet is an
# input now (BOX_SUBNET, setup-host.sh — #80), and a bridge moved off a
# colliding subnet must keep its firewall. setup-host runs us after the
# bridge exists, so the live read is the truth at install time; UFW rules
# persist across boots on their own, so the default only papers over the
# no-bridge-yet window at boot on a default-subnet host.
# ('|| true': under pipefail an absent bridge would kill the script here.)
GW="$(ip -4 -o addr show dev "$NET" 2>/dev/null | awk '{ split($4, a, "/"); print a[1]; exit }' || true)"
[ -n "$GW" ] || GW=10.88.0.1
if command -v ufw >/dev/null && ufw status 2>/dev/null | grep -q "Status: active"; then
if ! ufw status | grep "on $NET" | grep -q "DENY"; then

View file

@ -3,7 +3,7 @@
#
# The zero-ceremony transition is just install.sh + setup-host.sh: that leaves
# a DUAL-STACK host where legacy boxes (tag user.claudebox=1, claudenet/10.87,
# claude-dev) keep working while new mints land on boxnet/10.88. This script is
# claude-dev) keep working while new mints land on boxnet. This script is
# the two things that path does not do:
#
# migrate-host.sh --box <name> re-home ONE legacy box onto the new stack
@ -88,17 +88,19 @@ rehome_one() {
incus start "$b" >/dev/null 2>&1 || { warn "$b: did not restart — start it by hand"; return 1; }
# 3. VERIFY THE EFFECT, not the exit codes (the whole repo's lesson). The box
# must be on 10.88 and actually resolve+reach the internet on its new leg
# before we call it migrated.
local _i ip
# must be on boxnet's subnet (read off the network — BOX_SUBNET moves it,
# #80) and actually resolve+reach the internet on its new leg before we
# call it migrated.
local _i ip pfx
pfx="$(incus network get boxnet ipv4.address 2>/dev/null | cut -d/ -f1)"; pfx="${pfx%.*}."
ip=""
for _i in $(seq 1 30); do
ip="$(incus exec "$b" -- ip -4 -o addr show scope global </dev/null 2>/dev/null \
| awk '{for(i=1;i<NF;i++) if($i=="inet" && $(i+1)~/^10\.88\./){split($(i+1),a,"/"); print a[1]; exit}}')"
| awk -v p="$pfx" '{for(i=1;i<NF;i++) if($i=="inet" && index($(i+1),p)==1){split($(i+1),a,"/"); print a[1]; exit}}')"
[ -n "$ip" ] && break
sleep 2
done
[ -n "$ip" ] || { warn "$b: never got a 10.88 address after restart — re-home INCOMPLETE, inspect: incus console $b"; return 1; }
[ -n "$ip" ] || { warn "$b: never got a boxnet address after restart — re-home INCOMPLETE, inspect: incus console $b"; return 1; }
if incus exec "$b" -- getent hosts deb.debian.org </dev/null >/dev/null 2>&1; then
# LAST, and only once the move is VERIFIED: drop the legacy tag. Until this
# point the box wears both tags, so a failure anywhere above leaves it a

View file

@ -45,6 +45,88 @@ else
exit 1
fi
# --- The subnet, and the refusal to build on one something already owns -----
# (#80.) The stack's subnet was hardcoded, and running setup-host INSIDE a box
# gave the guest a nested boxnet claiming the exact subnet and gateway of its
# own uplink: the guest then held its gateway's address as a LOCAL address,
# carried two connected routes for the subnet, and suffered intermittent,
# self-recovering egress blackouts nobody could attribute — the host looked
# clean the whole time. The flagship use case funnels agents toward doing
# exactly this (working on box, in a box), so the guard must refuse BEFORE
# any mutation, and name the way out (BOX_SUBNET).
# BOX_SUBNET must be a /24 with a zero host octet — a.b.c.0/24. Everything
# the stack derives (the bridge address, the gateway carve-out, the firewall)
# assumes that shape, and a garbage value must die HERE, never inside an
# incus create or an nft rule.
valid_subnet() {
local o a="" b="" c="" rest=""
case "$1" in *.0/24) ;; *) return 1 ;; esac
IFS=. read -r a b c rest <<<"${1%/24}"
[ "$rest" = 0 ] || return 1
for o in "$a" "$b" "$c"; do
case "$o" in ''|*[!0-9]*) return 1 ;; esac
[ "${#o}" -le 3 ] && [ "$o" -le 255 ] || return 1
done
}
# Who, other than box's own bridge, already owns an address inside $1?
# Prints the claimant and succeeds when the subnet is claimed by a FOREIGNER;
# stays silent and fails when it is free — or held only by boxnet, which is
# the legitimate re-run, converging a stack this script built before. The
# most telling claimant is the default route's gateway: if it sits inside the
# target subnet, this machine's own uplink lives there — i.e. this is almost
# certainly the inside of a box. Pure over `ip` output, so test/cli.sh can
# drive it against canned tables with a shim ip.
subnet_claimant() {
local pfx hit
pfx="${1%0/24}"
hit="$(ip -4 route show default 2>/dev/null | awk -v p="$pfx" '
{ gw = ""; dev = ""
for (i = 1; i < NF; i++) { if ($i == "via") gw = $(i+1); if ($i == "dev") dev = $(i+1) }
if (index(gw, p) == 1 && dev != "boxnet") {
print "this machine\047s own DEFAULT GATEWAY (" gw " via " dev ")"; exit } }')"
if [ -z "$hit" ]; then
hit="$(ip -4 -o addr show 2>/dev/null | awk -v p="$pfx" '
$2 != "boxnet" && index($4, p) == 1 { print "interface " $2 " (" $4 ")"; exit }')"
fi
[ -n "$hit" ] && printf '%s\n' "$hit"
}
BOX_SUBNET="${BOX_SUBNET:-10.88.0.0/24}"
if ! valid_subnet "$BOX_SUBNET"; then
echo "ERROR: BOX_SUBNET='$BOX_SUBNET' is not a sane subnet — the stack takes a" >&2
echo " /24 with a zero host octet, e.g. BOX_SUBNET=10.89.0.0/24" >&2
exit 1
fi
BOX_GW="${BOX_SUBNET%.0/24}.1"
if hit="$(subnet_claimant "$BOX_SUBNET")"; then
echo "ERROR: refusing to build boxnet on $BOX_SUBNET — that subnet is already" >&2
echo " claimed here by $hit." >&2
echo " If that is this machine's uplink, you are INSIDE a box: a nested" >&2
echo " stack on the guest's own subnet captures its gateway address and" >&2
echo " blackholes its egress, intermittently (issue #80)." >&2
echo " Nothing was changed. To build a nested stack anyway, pick a free" >&2
echo " subnet: BOX_SUBNET=10.89.0.0/24 box setup-host" >&2
exit 1
fi
# A bridge this script built before is the one claimant that is NOT a
# collision — but it must AGREE with the target: setup-host converges an
# existing bridge, it never re-addresses one (boxes hold leases on it).
# ('|| true': under pipefail, `ip … dev boxnet` on a fresh host — no such
# device — would kill the script right here instead of answering "no bridge".)
have_gw="$(ip -4 -o addr show dev boxnet 2>/dev/null | awk '{ split($4, a, "/"); print a[1]; exit }' || true)"
if [ -n "$have_gw" ] && [ "$have_gw" != "$BOX_GW" ]; then
echo "ERROR: boxnet already exists on ${have_gw%.*}.0/24 and the target is $BOX_SUBNET" >&2
echo " setup-host converges an existing bridge, it never re-addresses one." >&2
echo " Re-run with the bridge's own subnet:" >&2
echo " BOX_SUBNET=${have_gw%.*}.0/24 box setup-host" >&2
echo " (or move the bridge first: incus network set boxnet ipv4.address $BOX_GW/24)" >&2
exit 1
fi
# apt, unattended-safe. install.sh now runs us without a human watching, and
# a fresh cloud image has apt-daily/unattended-upgrades holding the dpkg lock
# for the first minutes of its life — plain 'apt-get install' then waits on it
@ -145,22 +227,45 @@ PRESEED
fi
# Isolated NAT network. IPv6 off: one less egress path to reason about.
# 10.88, not 10.87: a pre-rename host may still carry claudenet on 10.87 with
# legacy boxes attached — two bridges must not claim one subnet.
# The default is 10.88 — not 10.87: a pre-rename host may still carry
# claudenet on 10.87 with legacy boxes attached — two bridges must not claim
# one subnet. BOX_SUBNET (validated and cleared by the #80 guard above) picks
# another /24; the gateway and every rule below derive from it.
incus network show boxnet >/dev/null 2>&1 || incus network create boxnet \
ipv4.address=10.88.0.1/24 ipv4.nat=true ipv6.address=none
ipv4.address="$BOX_GW/24" ipv4.nat=true ipv6.address=none
# ACL: default egress allow (internet), explicit drops for private space.
# Gateway carve-out first so instance DNS (dnsmasq on 10.88.0.1) survives.
if ! incus network acl show box-isolate >/dev/null 2>&1; then
incus network acl create box-isolate
incus network acl rule add box-isolate egress action=allow destination=10.88.0.1/32
incus network acl rule add box-isolate egress action=drop destination=10.0.0.0/8
incus network acl rule add box-isolate egress action=drop destination=172.16.0.0/12
incus network acl rule add box-isolate egress action=drop destination=192.168.0.0/16
incus network acl rule add box-isolate egress action=drop destination=169.254.0.0/16
incus network acl rule add box-isolate egress action=drop destination=100.64.0.0/10
fi
# Gateway carve-out first so instance DNS (dnsmasq on the gateway) survives.
# 'edit' the full shipped ruleset, not create-once: the carve-out derives
# from BOX_SUBNET now, and a bridge moved off a colliding subnet (#80's
# escape hatch) left the OLD /32 behind — box DNS to the new gateway then
# died inside the 10.0.0.0/8 drop, looking like a dead resolver, not a stale
# ACL. A conditional 'rule add' cannot converge that (the stale carve-out
# would survive beside the new one); replacing the ruleset does, idempotently.
incus network acl show box-isolate >/dev/null 2>&1 || incus network acl create box-isolate
incus network acl edit box-isolate <<ACL
description: ""
egress:
- action: allow
destination: $BOX_GW/32
state: enabled
- action: drop
destination: 10.0.0.0/8
state: enabled
- action: drop
destination: 172.16.0.0/12
state: enabled
- action: drop
destination: 192.168.0.0/16
state: enabled
- action: drop
destination: 169.254.0.0/16
state: enabled
- action: drop
destination: 100.64.0.0/10
state: enabled
ingress: []
ACL
incus network set boxnet security.acls=box-isolate \
security.acls.default.egress.action=allow \
security.acls.default.ingress.action=drop