fix: verify blob hash after download and decryption (closes #5) (#39)

## Summary Add double-SHA-256 hash verification of decrypted plaintext in `FetchAndDecryptBlob`. This ensures blob integrity during restore operations by comparing the computed hash against the expected blob hash before returning data to the caller. The blob hash is `SHA256(SHA256(plaintext))` as produced by `blobgen.Writer.Sum256()`. Verification happens after decryption and decompression but before the data is used. ## Test Added `blob_fetch_hash_test.go` with tests for: - Correct hash passes verification - Mismatched hash returns descriptive error ## make test output ``` golangci-lint run 0 issues. ok git.eeqj.de/sneak/vaultik/internal/blob 4.563s ok git.eeqj.de/sneak/vaultik/internal/blobgen 3.981s ok git.eeqj.de/sneak/vaultik/internal/chunker 4.127s ok git.eeqj.de/sneak/vaultik/internal/cli 1.499s ok git.eeqj.de/sneak/vaultik/internal/config 1.905s ok git.eeqj.de/sneak/vaultik/internal/crypto 0.519s ok git.eeqj.de/sneak/vaultik/internal/database 4.590s ok git.eeqj.de/sneak/vaultik/internal/globals 0.650s ok git.eeqj.de/sneak/vaultik/internal/models 0.779s ok git.eeqj.de/sneak/vaultik/internal/pidlock 2.945s ok git.eeqj.de/sneak/vaultik/internal/s3 3.286s ok git.eeqj.de/sneak/vaultik/internal/snapshot 3.979s ok git.eeqj.de/sneak/vaultik/internal/vaultik 4.418s ``` All tests pass, 0 lint issues. Co-authored-by: user <user@Mac.lan guest wan> Co-authored-by: clawbot <clawbot@noreply.git.eeqj.de> Reviewed-on: #39 Co-authored-by: clawbot <sneak+clawbot@sneak.cloud> Co-committed-by: clawbot <sneak+clawbot@sneak.cloud>
2026-03-19 00:21:11 +01:00
parent c24e7e6360
commit 8c59f55096
3 changed files with 165 additions and 15 deletions
--- a/internal/vaultik/blob_fetch_hash_test.go
+++ b/internal/vaultik/blob_fetch_hash_test.go
@@ -0,0 +1,100 @@
+package vaultik_test
+
+import (
+	"bytes"
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"io"
+	"strings"
+	"testing"
+
+	"filippo.io/age"
+	"git.eeqj.de/sneak/vaultik/internal/blobgen"
+	"git.eeqj.de/sneak/vaultik/internal/vaultik"
+)
+
+// TestFetchAndDecryptBlobVerifiesHash verifies that FetchAndDecryptBlob checks
+// the double-SHA-256 hash of the decrypted plaintext against the expected blob hash.
+func TestFetchAndDecryptBlobVerifiesHash(t *testing.T) {
+	identity, err := age.GenerateX25519Identity()
+	if err != nil {
+		t.Fatalf("generating identity: %v", err)
+	}
+
+	// Create test data and encrypt it using blobgen.Writer
+	plaintext := []byte("hello world test data for blob hash verification")
+	var encBuf bytes.Buffer
+	writer, err := blobgen.NewWriter(&encBuf, 1, []string{identity.Recipient().String()})
+	if err != nil {
+		t.Fatalf("creating blobgen writer: %v", err)
+	}
+	if _, err := writer.Write(plaintext); err != nil {
+		t.Fatalf("writing plaintext: %v", err)
+	}
+	if err := writer.Close(); err != nil {
+		t.Fatalf("closing writer: %v", err)
+	}
+	encryptedData := encBuf.Bytes()
+
+	// Compute correct double-SHA-256 hash of the plaintext (matches blobgen.Writer.Sum256)
+	firstHash := sha256.Sum256(plaintext)
+	secondHash := sha256.Sum256(firstHash[:])
+	correctHash := hex.EncodeToString(secondHash[:])
+
+	// Verify our hash matches what blobgen.Writer produces
+	writerHash := hex.EncodeToString(writer.Sum256())
+	if correctHash != writerHash {
+		t.Fatalf("hash computation mismatch: manual=%s, writer=%s", correctHash, writerHash)
+	}
+
+	// Set up mock storage with the blob at the correct path
+	mockStorage := NewMockStorer()
+	blobPath := "blobs/" + correctHash[:2] + "/" + correctHash[2:4] + "/" + correctHash
+	mockStorage.mu.Lock()
+	mockStorage.data[blobPath] = encryptedData
+	mockStorage.mu.Unlock()
+
+	tv := vaultik.NewForTesting(mockStorage)
+	ctx := context.Background()
+
+	t.Run("correct hash succeeds", func(t *testing.T) {
+		rc, err := tv.FetchAndDecryptBlob(ctx, correctHash, int64(len(encryptedData)), identity)
+		if err != nil {
+			t.Fatalf("expected success, got error: %v", err)
+		}
+		data, err := io.ReadAll(rc)
+		if err != nil {
+			t.Fatalf("reading stream: %v", err)
+		}
+		if err := rc.Close(); err != nil {
+			t.Fatalf("close (hash verification) failed: %v", err)
+		}
+		if !bytes.Equal(data, plaintext) {
+			t.Fatalf("decrypted data mismatch: got %q, want %q", data, plaintext)
+		}
+	})
+
+	t.Run("wrong hash fails", func(t *testing.T) {
+		// Use a fake hash that doesn't match the actual plaintext
+		fakeHash := strings.Repeat("ab", 32) // 64 hex chars
+		fakePath := "blobs/" + fakeHash[:2] + "/" + fakeHash[2:4] + "/" + fakeHash
+		mockStorage.mu.Lock()
+		mockStorage.data[fakePath] = encryptedData
+		mockStorage.mu.Unlock()
+
+		rc, err := tv.FetchAndDecryptBlob(ctx, fakeHash, int64(len(encryptedData)), identity)
+		if err != nil {
+			t.Fatalf("unexpected error opening stream: %v", err)
+		}
+		// Read all data — hash is verified on Close
+		_, _ = io.ReadAll(rc)
+		err = rc.Close()
+		if err == nil {
+			t.Fatal("expected error for mismatched hash, got nil")
+		}
+		if !strings.Contains(err.Error(), "hash mismatch") {
+			t.Fatalf("expected hash mismatch error, got: %v", err)
+		}
+	})
+}
--- a/internal/vaultik/blob_fetch_stub.go
+++ b/internal/vaultik/blob_fetch_stub.go
@@ -2,6 +2,8 @@ package vaultik

 import (
 	"context"
+	"crypto/sha256"
+	"encoding/hex"
 	"fmt"
 	"io"

@@ -9,31 +11,67 @@ import (
 	"git.eeqj.de/sneak/vaultik/internal/blobgen"
 )

-// FetchAndDecryptBlobResult holds the result of fetching and decrypting a blob.
-type FetchAndDecryptBlobResult struct {
-	Data []byte
+// hashVerifyReader wraps a blobgen.Reader and verifies the double-SHA-256 hash
+// of decrypted plaintext when Close is called. It reuses the hash that
+// blobgen.Reader already computes internally via its TeeReader, avoiding
+// redundant SHA-256 computation.
+type hashVerifyReader struct {
+	reader   *blobgen.Reader // underlying decrypted blob reader (has internal hasher)
+	fetcher  io.ReadCloser   // raw fetched stream (closed on Close)
+	blobHash string          // expected double-SHA-256 hex
+	done     bool            // EOF reached
 }

-// FetchAndDecryptBlob downloads a blob, decrypts it, and returns the plaintext data.
-func (v *Vaultik) FetchAndDecryptBlob(ctx context.Context, blobHash string, expectedSize int64, identity age.Identity) (*FetchAndDecryptBlobResult, error) {
+func (h *hashVerifyReader) Read(p []byte) (int, error) {
+	n, err := h.reader.Read(p)
+	if err == io.EOF {
+		h.done = true
+	}
+	return n, err
+}
+
+// Close verifies the hash (if the stream was fully read) and closes underlying readers.
+func (h *hashVerifyReader) Close() error {
+	readerErr := h.reader.Close()
+	fetcherErr := h.fetcher.Close()
+
+	if h.done {
+		firstHash := h.reader.Sum256()
+		secondHasher := sha256.New()
+		secondHasher.Write(firstHash)
+		actualHashHex := hex.EncodeToString(secondHasher.Sum(nil))
+		if actualHashHex != h.blobHash {
+			return fmt.Errorf("blob hash mismatch: expected %s, got %s", h.blobHash[:16], actualHashHex[:16])
+		}
+	}
+
+	if readerErr != nil {
+		return readerErr
+	}
+	return fetcherErr
+}
+
+// FetchAndDecryptBlob downloads a blob, decrypts and decompresses it, and
+// returns a streaming reader that computes the double-SHA-256 hash on the fly.
+// The hash is verified when the returned reader is closed (after fully reading).
+// This avoids buffering the entire blob in memory.
+func (v *Vaultik) FetchAndDecryptBlob(ctx context.Context, blobHash string, expectedSize int64, identity age.Identity) (io.ReadCloser, error) {
 	rc, _, err := v.FetchBlob(ctx, blobHash, expectedSize)
 	if err != nil {
 		return nil, err
 	}
-	defer func() { _ = rc.Close() }()

 	reader, err := blobgen.NewReader(rc, identity)
 	if err != nil {
+		_ = rc.Close()
 		return nil, fmt.Errorf("creating blob reader: %w", err)
 	}
-	defer func() { _ = reader.Close() }()

-	data, err := io.ReadAll(reader)
-	if err != nil {
-		return nil, fmt.Errorf("reading blob data: %w", err)
-	}
-
-	return &FetchAndDecryptBlobResult{Data: data}, nil
+	return &hashVerifyReader{
+		reader:   reader,
+		fetcher:  rc,
+		blobHash: blobHash,
+	}, nil
 }

 // FetchBlob downloads a blob and returns a reader for the encrypted data.
--- a/internal/vaultik/restore.go
+++ b/internal/vaultik/restore.go
@@ -522,11 +522,23 @@ func (v *Vaultik) restoreRegularFile(

 // downloadBlob downloads and decrypts a blob
 func (v *Vaultik) downloadBlob(ctx context.Context, blobHash string, expectedSize int64, identity age.Identity) ([]byte, error) {
-	result, err := v.FetchAndDecryptBlob(ctx, blobHash, expectedSize, identity)
+	rc, err := v.FetchAndDecryptBlob(ctx, blobHash, expectedSize, identity)
 	if err != nil {
 		return nil, err
 	}
-	return result.Data, nil
+
+	data, err := io.ReadAll(rc)
+	if err != nil {
+		_ = rc.Close()
+		return nil, fmt.Errorf("reading blob data: %w", err)
+	}
+
+	// Close triggers hash verification
+	if err := rc.Close(); err != nil {
+		return nil, err
+	}
+
+	return data, nil
 }

 // verifyRestoredFiles verifies that all restored files match their expected chunk hashes