nixos/scripts/secrets/rotate-admin-key.sh

#!/usr/bin/env bash
# Rotates the &admin sops age key: decrypts with a backed-up copy of the
# key CURRENTLY trusted as &admin, replaces .sops.yaml's &admin entry with
# a new key already present in this environment, and re-encrypts every
# secrets/*.yaml for the new recipient set. After this runs, the old key
# can no longer decrypt anything -- this is a real, one-way handoff of
# trust, not a preview.
#
# This is the automation for the manual steps create-proxmox-resource.sh /
# sync-host-keys.sh print when they bootstrap a brand-new, not-yet-trusted
# age key on a machine that's never had admin access before:
#
#   scripts/secrets/rotate-admin-key.sh /path/to/backed-up/admin/keys.txt
#
# The backup key's *public* key must match .sops.yaml's current &admin
# entry -- this script verifies that by deriving it, it doesn't just trust
# the filename or take it on faith. The new key defaults to wherever sops
# itself would already look ($SOPS_AGE_KEY_FILE, then the XDG default), so
# the common case is just pointing this at the restored backup.
set -euo pipefail

repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
sops_yaml="${repo_root}/.sops.yaml"

# shellcheck source=../env.sh
source "${repo_root}/scripts/env.sh"
# shellcheck source=../lib/sops-age.sh
source "${repo_root}/scripts/lib/sops-age.sh"

# sops resolves .sops.yaml by walking up from the process's cwd, not from
# the target file's own path -- if this script were invoked from somewhere
# other than the repo root (or from inside another checkout/worktree that
# happens to have its own .sops.yaml), `sops updatekeys` would silently
# re-encrypt against the WRONG config's recipient list instead of this
# repo's. Pin cwd here so every sops/age call below is unambiguous
# regardless of where the caller's shell started out.
cd "$repo_root"

usage() {
  cat <<EOF
Usage: $0 <path-to-backed-up-admin-key> [--new-key-file <path>] [--dry-run]

  <path-to-backed-up-admin-key>  age identity file for the key CURRENTLY
                                 trusted as &admin. Only ever read -- never
                                 copied or modified.
  --new-key-file <path>          age identity file for the key to promote
                                 to &admin. Defaults to \$SOPS_AGE_KEY_FILE,
                                 then
                                 \${XDG_CONFIG_HOME:-\$HOME/.config}/sops/age/keys.txt
                                 (sops/age's own default resolution order).
  --dry-run                      Print what would change; touches nothing
                                  (.sops.yaml untouched, no sops updatekeys
                                  calls).
EOF
}

dry_run=0
new_key_file="$DEFAULT_SOPS_AGE_KEY_FILE"
args=()

while [[ $# -gt 0 ]]; do
  case "$1" in
    --dry-run)
      dry_run=1
      shift
      ;;
    --new-key-file)
      new_key_file="${2:?--new-key-file requires a path}"
      shift 2
      ;;
    -h | --help)
      usage
      exit 0
      ;;
    --*)
      echo "Unknown option: $1" >&2
      usage >&2
      exit 1
      ;;
    *)
      args+=("$1")
      shift
      ;;
  esac
done

if [[ "${#args[@]}" -ne 1 ]]; then
  usage >&2
  exit 1
fi
backup_key="${args[0]}"

[[ -s "$backup_key" ]] || { echo "ERROR: backup key file not found or empty: ${backup_key}" >&2; exit 1; }
[[ -s "$new_key_file" ]] || { echo "ERROR: new key file not found or empty: ${new_key_file}" >&2; exit 1; }

nix_extra_opts

echo "==> Deriving public keys..."
old_pub="$(age_pubkey_from_identity_file "$backup_key")"
new_pub="$(age_pubkey_from_identity_file "$new_key_file")"
echo "    backup (old admin) key: ${old_pub}"
echo "    new admin key:          ${new_pub}"

if [[ "$old_pub" == "$new_pub" ]]; then
  echo "ERROR: backup key and new key are identical -- nothing to rotate." >&2
  exit 1
fi

current_admin_pub="$(sops_yaml_admin_pubkey "$sops_yaml")"
if [[ -z "$current_admin_pub" ]]; then
  echo "ERROR: couldn't find a '&admin age1...' line in ${sops_yaml}." >&2
  exit 1
fi

if [[ "$current_admin_pub" != "$old_pub" ]]; then
  echo "ERROR: ${backup_key} doesn't match the current &admin key in .sops.yaml." >&2
  echo "  .sops.yaml &admin: ${current_admin_pub}" >&2
  echo "  backup key pubkey: ${old_pub}" >&2
  echo "Wrong backup file, or .sops.yaml has already moved on -- not touching anything." >&2
  exit 1
fi

mapfile -t secrets_files < <(find "${repo_root}/secrets" -maxdepth 1 -name '*.yaml' | sort)
if [[ "${#secrets_files[@]}" -eq 0 ]]; then
  echo "ERROR: no secrets/*.yaml files found under ${repo_root}/secrets." >&2
  exit 1
fi

# sops_can_decrypt <key-file> <secrets-file>: used both to confirm the
# backup key still works before touching anything, and again after
# rotation to confirm the new key does too.
sops_can_decrypt() {
  local key_file="$1" secrets_file="$2"
  SOPS_AGE_KEY_FILE="$key_file" nix-shell "${NIX_OPTS[@]}" -p sops --run \
    "sops -d '${secrets_file}'" >/dev/null
}

echo "==> Confirming the backup key can actually decrypt..."
if ! sops_can_decrypt "$backup_key" "${secrets_files[0]}"; then
  echo "ERROR: backup key failed to decrypt $(basename "${secrets_files[0]}") -- aborting." >&2
  exit 1
fi
echo "    OK: decrypted $(basename "${secrets_files[0]}")"

if [[ "$dry_run" -eq 1 ]]; then
  echo
  echo "[dry-run] would replace .sops.yaml's &admin line:"
  echo "[dry-run]   - ${current_admin_pub}"
  echo "[dry-run]   + ${new_pub}"
  echo "[dry-run] would then re-encrypt (sops updatekeys --yes) for the new recipient set:"
  for f in "${secrets_files[@]}"; do
    echo "[dry-run]   secrets/$(basename "$f")"
  done
  echo
  echo "[dry-run] Nothing was changed. Re-run without --dry-run to apply this."
  exit 0
fi

echo "==> Rotating .sops.yaml's &admin key..."
sed -i "s|^  - &admin age1[a-z0-9]*|  - \&admin ${new_pub}|" "$sops_yaml"
grep -qF "$new_pub" "$sops_yaml" || {
  echo "ERROR: sed edit didn't take -- .sops.yaml left unchanged, check it by hand." >&2
  exit 1
}
echo "    Updated."

echo "==> Re-encrypting secrets/*.yaml for the new recipient set..."
for f in "${secrets_files[@]}"; do
  echo "==> $(basename "$f")"
  sops_updatekeys "$f" "$backup_key"
done

echo "==> Verifying the new key can decrypt everything..."
for f in "${secrets_files[@]}"; do
  if ! sops_can_decrypt "$new_key_file" "$f"; then
    echo "ERROR: new key failed to decrypt $(basename "$f") after rotation -- investigate before committing." >&2
    exit 1
  fi
  echo "    OK: $(basename "$f")"
done

cat <<EOF

Done. .sops.yaml's &admin key is now:
  ${new_pub}

The old key (${old_pub}) can no longer decrypt any secrets/*.yaml
re-encrypted above.

Review the diff, then commit:
  git add .sops.yaml secrets/*.yaml
  git commit -m "Rotate sops admin age key"
EOF