fix(ingestion): every brain/raw/ reader goes through an os.Root; symlinks are inert
raw/ is writable via Syncthing (a sendreceive folder shared with flamingo, symlinks synced) and by the brain CronJobs, and several readers followed symlinks out of it: - /pending and brain_pending showed a symlink target's contents; brain_promote would copy it into wiki/ (then brain-sync to Gitea); brain_reject would copy it into raw/rejected/. - The watcher, which needs no API call at all, ingested symlinked files (WalkDir yields them; extract.Text followed them). Not in the issue; found while fixing it. - Ingest checked a path then reopened it by name (TOCTOU). OpenRawRoot opens brain/raw as an os.Root and refuses a raw/ that is itself a symlink. ListPending, PromoteNote and RejectNote read through it and refuse anything not a regular file. extract.TextIn reads through a root (temp copy for pdf/docmark); /ingest-path, brain_ingest and the watcher use it, and the watcher archives via the root too, so a file swapped for a symlink after a check still cannot lead out. Refs #153 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -7,6 +7,7 @@ import (
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -282,3 +283,32 @@ func TestProcessDir_SkipsTunnelCandidateFiles(t *testing.T) {
|
||||
_, err = os.Stat(filepath.Join(brainDir, "raw", "processed", date, "tunnel-candidates-2026-07-19.md"))
|
||||
assert.True(t, os.IsNotExist(err), "tunnel-candidates file should not be copied to processed/")
|
||||
}
|
||||
|
||||
// hyperguild#153: raw/ is writable via Syncthing, and the watcher ingests
|
||||
// whatever lands there with no API call at all. WalkDir yields symlinked
|
||||
// files, and extract.Text followed them, so a symlink to any pod-readable
|
||||
// file would be extracted into the brain. The watcher now ingests only
|
||||
// regular files, read through an os.Root on raw/.
|
||||
func TestProcessDir_DoesNotIngestSymlinks(t *testing.T) {
|
||||
brainDir := setupBrainDir(t)
|
||||
outside := filepath.Join(t.TempDir(), "secret.md")
|
||||
require.NoError(t, os.WriteFile(outside, []byte("SENTINEL-153-WATCHER"), 0o644))
|
||||
require.NoError(t, os.Symlink(outside, filepath.Join(brainDir, "raw", "leak.md")))
|
||||
|
||||
var sawSentinel bool
|
||||
calls := 0
|
||||
cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{
|
||||
Complete: func(_ context.Context, _, user string) (string, error) {
|
||||
calls++
|
||||
if strings.Contains(user, "SENTINEL-153-WATCHER") {
|
||||
sawSentinel = true
|
||||
}
|
||||
b, _ := json.Marshal([]pipeline.RawPage{{Title: "X", Type: "source", Subtype: "article", Content: "## S\n\nx\n"}})
|
||||
return string(b), nil
|
||||
},
|
||||
Schema: "# Schema",
|
||||
}}
|
||||
_ = processDir(context.Background(), cfg, time.Now().UTC().Format("2006-01-02"))
|
||||
assert.False(t, sawSentinel, "the symlink target must never reach the pipeline")
|
||||
assert.Zero(t, calls, "a symlink is not a note")
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user