banger/internal/daemon/ssh_client_config.go
Thales Maciel ae14b9499d
ssh: trust-on-first-use host key pinning everywhere
Guest host-key verification was off in all three SSH paths:

  * Go SSH (internal/guest/ssh.go) used ssh.InsecureIgnoreHostKey
  * `banger vm ssh` passed StrictHostKeyChecking=no
    + UserKnownHostsFile=/dev/null
  * `~/.ssh/config` Host *.vm shipped the same posture into the
    user's global config

Now each path verifies against a banger-owned known_hosts file at
`~/.local/state/banger/ssh/known_hosts` with TOFU semantics:

  * First dial to a VM pins the key.
  * Subsequent dials require an exact match. A mismatch fails with
    an explicit "possible MITM" error.
  * `vm delete` removes the entries so a future VM reusing the IP
    or name re-pins cleanly.
  * The user's `~/.ssh/known_hosts` is untouched.

Changes:

  internal/guest/known_hosts.go (new) — OpenSSH-compatible parser,
    TOFUHostKeyCallback, RemoveKnownHosts. Process-wide mutex
    around the file.
  internal/guest/ssh.go — Dial and WaitForSSH grew a knownHostsPath
    parameter threaded through the callback. Empty path keeps the
    insecure callback (tests + throwaway tools only; documented).
  internal/daemon/{guest_sessions,session_attach,session_lifecycle,
    session_stream}.go — call sites pass d.layout.KnownHostsPath.
  internal/daemon/ssh_client_config.go — the ~/.ssh/config Host *.vm
    block now points at banger's known_hosts and uses
    StrictHostKeyChecking=accept-new. Missing path → fail closed.
  internal/daemon/vm_lifecycle.go — deleteVMLocked drops known_hosts
    entries for the VM's IP and DNS name via removeVMKnownHosts.
  internal/cli/banger.go — sshCommandArgs swaps StrictHostKeyChecking
    no + /dev/null for banger's file + accept-new. Path resolution
    failure falls through to StrictHostKeyChecking=yes.
  internal/paths/paths.go — Layout gains SSHDir + KnownHostsPath;
    Ensure creates SSHDir at 0700.

Tests (internal/guest/known_hosts_test.go): pin on first use, accept
matching key on second dial, reject mismatch, empty path skips
checking, RemoveKnownHosts drops the entry, re-pin works after
remove. Existing daemon + cli tests updated to assert the new
posture and regression-guard against the old flags.

Live verified: vm run writes the pin to banger's known_hosts at 0600
inside a 0700 dir; banger vm ssh + ssh root@<vm>.vm both succeed
using the pin; vm delete clears it.
2026-04-19 16:46:03 -03:00

178 lines
5 KiB
Go

package daemon
import (
"fmt"
"log/slog"
"os"
"path/filepath"
"strings"
"banger/internal/guest"
"banger/internal/model"
"banger/internal/paths"
)
// removeVMKnownHosts drops every host-key pin for vm from the
// banger-owned known_hosts. Best-effort — a failure here only
// matters if the same IP/name is reused by a fresh VM before the
// next daemon restart, and even then it just causes a
// TOFU-mismatch error that the user can clear manually. Logged at
// warn so it shows up if it ever actually breaks things.
func removeVMKnownHosts(knownHostsPath string, vm model.VMRecord, logger *slog.Logger) {
if strings.TrimSpace(knownHostsPath) == "" {
return
}
var hosts []string
if ip := strings.TrimSpace(vm.Runtime.GuestIP); ip != "" {
hosts = append(hosts, ip)
}
if dns := strings.TrimSpace(vm.Runtime.DNSName); dns != "" {
hosts = append(hosts, dns)
}
if len(hosts) == 0 {
return
}
if err := guest.RemoveKnownHosts(knownHostsPath, hosts...); err != nil && logger != nil {
logger.Warn("remove known_hosts entries", "vm_id", vm.ID, "error", err.Error())
}
}
const (
vmSSHConfigIncludeBegin = "# BEGIN BANGER MANAGED VM SSH"
vmSSHConfigIncludeEnd = "# END BANGER MANAGED VM SSH"
)
func (d *Daemon) ensureVMSSHClientConfig() {
if err := syncVMSSHClientConfig(d.layout, d.config.SSHKeyPath); err != nil && d.logger != nil {
d.logger.Warn("vm ssh client config sync failed", "error", err.Error())
}
}
func syncVMSSHClientConfig(layout paths.Layout, keyPath string) error {
keyPath = strings.TrimSpace(keyPath)
if keyPath == "" {
return nil
}
home, err := os.UserHomeDir()
if err != nil {
return err
}
sshDir := filepath.Join(home, ".ssh")
if err := os.MkdirAll(sshDir, 0o700); err != nil {
return err
}
userConfigPath := filepath.Join(sshDir, "config")
userConfig, err := readTextFileIfExists(userConfigPath)
if err != nil {
return err
}
updated, err := upsertManagedBlock(userConfig, vmSSHConfigIncludeBegin, vmSSHConfigIncludeEnd, renderManagedVMSSHBlock(keyPath, layout.KnownHostsPath))
if err != nil {
return err
}
if err := writeTextFileIfChanged(userConfigPath, updated, 0o644); err != nil {
return err
}
legacyManagedPath := filepath.Join(layout.ConfigDir, "ssh", "ssh_config")
if err := os.Remove(legacyManagedPath); err != nil && !os.IsNotExist(err) {
return err
}
return nil
}
// renderManagedVMSSHBlock produces the `Host *.vm` stanza banger
// writes into the user's ~/.ssh/config. Host-key verification uses
// the banger-owned known_hosts file at knownHostsPath — NOT the
// user's ~/.ssh/known_hosts, and NOT /dev/null. `accept-new` means
// first contact pins the key; any later mismatch fails the connect.
func renderManagedVMSSHBlock(keyPath, knownHostsPath string) string {
keyPath = strings.TrimSpace(keyPath)
knownHostsPath = strings.TrimSpace(knownHostsPath)
lines := []string{
vmSSHConfigIncludeBegin,
"# Generated by banger for direct SSH access to VM DNS names.",
"# Host keys are pinned on first use into a banger-owned",
"# known_hosts file (not ~/.ssh/known_hosts).",
"Host *.vm",
" User root",
" IdentityFile " + keyPath,
" IdentitiesOnly yes",
" BatchMode yes",
" PreferredAuthentications publickey",
" PasswordAuthentication no",
" KbdInteractiveAuthentication no",
}
if knownHostsPath != "" {
lines = append(lines,
" UserKnownHostsFile "+knownHostsPath,
" StrictHostKeyChecking accept-new",
)
} else {
// Missing known_hosts path is a configuration anomaly — fail
// closed rather than silently disable verification.
lines = append(lines, " StrictHostKeyChecking yes")
}
lines = append(lines,
" LogLevel ERROR",
vmSSHConfigIncludeEnd,
"",
)
return strings.Join(lines, "\n")
}
func upsertManagedBlock(existing, beginMarker, endMarker, block string) (string, error) {
existing = normalizeConfigText(existing)
block = normalizeConfigText(block)
start := strings.Index(existing, beginMarker)
if start >= 0 {
end := strings.Index(existing[start:], endMarker)
if end < 0 {
return "", fmt.Errorf("managed block %q is missing end marker %q", beginMarker, endMarker)
}
end += start + len(endMarker)
for end < len(existing) && existing[end] == '\n' {
end++
}
existing = strings.TrimRight(existing[:start]+existing[end:], "\n")
}
if strings.TrimSpace(existing) == "" {
return block, nil
}
return strings.TrimRight(existing, "\n") + "\n\n" + block, nil
}
func normalizeConfigText(text string) string {
text = strings.ReplaceAll(text, "\r\n", "\n")
text = strings.TrimRight(text, "\n")
if text == "" {
return ""
}
return text + "\n"
}
func readTextFileIfExists(path string) (string, error) {
data, err := os.ReadFile(path)
if err == nil {
return string(data), nil
}
if os.IsNotExist(err) {
return "", nil
}
return "", err
}
func writeTextFileIfChanged(path, content string, mode os.FileMode) error {
content = normalizeConfigText(content)
existing, err := readTextFileIfExists(path)
if err != nil {
return err
}
if existing == content {
return nil
}
return os.WriteFile(path, []byte(content), mode)
}