fix(pipeline): quote YAML scalar fields in buildFrontmatter to prevent injection

ingestion/internal/pipeline/build.go

@@ -48,7 +48,7 @@ func buildPage(rp RawPage, sourceSlug, date string) wiki.Page {
 func buildFrontmatter(rp RawPage, date string) string {
 	var sb strings.Builder
 	sb.WriteString("---\n")
-	fmt.Fprintf(&sb, "title: %s\n", rp.Title)
+	fmt.Fprintf(&sb, "title: %s\n", yamlScalar(rp.Title))
 
 	switch rp.Type {
 	case "source":
@@ -56,33 +56,37 @@ func buildFrontmatter(rp RawPage, date string) string {
 		if subtype == "" {
 			subtype = "article"
 		}
-		fmt.Fprintf(&sb, "type: %s\n", subtype)
+		fmt.Fprintf(&sb, "type: %s\n", yamlScalar(subtype))
 		if rp.Domain != "" {
-			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+			fmt.Fprintf(&sb, "domain: %s\n", yamlScalar(rp.Domain))
 		}
 		fmt.Fprintf(&sb, "date_ingested: %s\n", date)
 		fmt.Fprintf(&sb, "last_updated: %s\n", date)
 	case "concept":
 		if rp.Domain != "" {
-			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+			fmt.Fprintf(&sb, "domain: %s\n", yamlScalar(rp.Domain))
 		}
 		fmt.Fprintf(&sb, "last_updated: %s\n", date)
 	case "entity":
 		if rp.Subtype != "" {
-			fmt.Fprintf(&sb, "type: %s\n", rp.Subtype)
+			fmt.Fprintf(&sb, "type: %s\n", yamlScalar(rp.Subtype))
 		}
 		if rp.Domain != "" {
-			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+			fmt.Fprintf(&sb, "domain: %s\n", yamlScalar(rp.Domain))
 		}
 		fmt.Fprintf(&sb, "last_updated: %s\n", date)
 	default:
 		if rp.Domain != "" {
-			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+			fmt.Fprintf(&sb, "domain: %s\n", yamlScalar(rp.Domain))
 		}
 		fmt.Fprintf(&sb, "last_updated: %s\n", date)
 	}
 
-	fmt.Fprintf(&sb, "aliases:\n  - %s\n", rp.Title)
+	fmt.Fprintf(&sb, "aliases:\n  - %s\n", yamlScalar(rp.Title))
 	sb.WriteString("---\n")
 	return sb.String()
 }
+
+func yamlScalar(s string) string {
+	return "'" + strings.ReplaceAll(s, "'", "''") + "'"
+}

ingestion/internal/pipeline/build_test.go

@@ -24,12 +24,12 @@ func TestBuildPages_SourcePage(t *testing.T) {
 
 	p := pages[0]
 	assert.Equal(t, "wiki/sources/shape-up.md", p.Path)
-	assert.Contains(t, p.Content, "title: Shape Up")
+	assert.Contains(t, p.Content, "title: 'Shape Up'")
-	assert.Contains(t, p.Content, "type: book")
+	assert.Contains(t, p.Content, "type: 'book'")
-	assert.Contains(t, p.Content, "domain: product-strategy")
+	assert.Contains(t, p.Content, "domain: 'product-strategy'")
 	assert.Contains(t, p.Content, "date_ingested: 2026-04-23")
 	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
-	assert.Contains(t, p.Content, "aliases:\n  - Shape Up")
+	assert.Contains(t, p.Content, "aliases:\n  - 'Shape Up'")
 	assert.Contains(t, p.Content, "## Summary")
 	assert.True(t, strings.HasPrefix(p.Content, "---\n"), "content must start with frontmatter")
 }
@@ -48,10 +48,10 @@ func TestBuildPages_ConceptPage(t *testing.T) {
 
 	p := pages[0]
 	assert.Equal(t, "wiki/concepts/betting.md", p.Path)
-	assert.Contains(t, p.Content, "title: Betting")
+	assert.Contains(t, p.Content, "title: 'Betting'")
-	assert.Contains(t, p.Content, "domain: product-strategy")
+	assert.Contains(t, p.Content, "domain: 'product-strategy'")
 	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
-	assert.Contains(t, p.Content, "aliases:\n  - Betting")
+	assert.Contains(t, p.Content, "aliases:\n  - 'Betting'")
 	assert.NotContains(t, p.Content, "date_ingested")
 	assert.Contains(t, p.Content, "## Definition")
 }
@@ -71,11 +71,11 @@ func TestBuildPages_EntityPage(t *testing.T) {
 
 	p := pages[0]
 	assert.Equal(t, "wiki/entities/ryan-singer.md", p.Path)
-	assert.Contains(t, p.Content, "title: Ryan Singer")
+	assert.Contains(t, p.Content, "title: 'Ryan Singer'")
-	assert.Contains(t, p.Content, "type: person")
+	assert.Contains(t, p.Content, "type: 'person'")
-	assert.Contains(t, p.Content, "domain: product-strategy")
+	assert.Contains(t, p.Content, "domain: 'product-strategy'")
 	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
-	assert.Contains(t, p.Content, "aliases:\n  - Ryan Singer")
+	assert.Contains(t, p.Content, "aliases:\n  - 'Ryan Singer'")
 	assert.NotContains(t, p.Content, "date_ingested")
 }
 
@@ -105,7 +105,7 @@ func TestBuildPages_SourceDefaultSubtype(t *testing.T) {
 	}
 	pages := BuildPages(raw, "some-post", "2026-04-23")
 	require.Len(t, pages, 1)
-	assert.Contains(t, pages[0].Content, "type: article")
+	assert.Contains(t, pages[0].Content, "type: 'article'")
 }
 
 func TestBuildPages_OmitsDomainWhenEmpty(t *testing.T) {
@@ -129,3 +129,24 @@ func TestBuildPages_MultiplePages(t *testing.T) {
 	assert.Equal(t, "wiki/concepts/betting.md", pages[1].Path)
 	assert.Equal(t, "wiki/entities/ryan-singer.md", pages[2].Path)
 }
+
+func TestBuildPages_TitleWithColon(t *testing.T) {
+	raw := []RawPage{
+		{Title: "Shape Up: The Basecamp Method", Type: "source", Subtype: "book", Content: "## Summary\n\nA book.\n"},
+	}
+	pages := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 1)
+	// Title with colon must be quoted in YAML
+	assert.Contains(t, pages[0].Content, "title: 'Shape Up: The Basecamp Method'")
+	assert.Contains(t, pages[0].Content, "aliases:\n  - 'Shape Up: The Basecamp Method'")
+}
+
+func TestBuildPages_EntityNoSubtype(t *testing.T) {
+	raw := []RawPage{
+		{Title: "Basecamp", Type: "entity", Content: "## Description\n\nA company.\n"},
+	}
+	pages := BuildPages(raw, "src", "2026-04-23")
+	require.Len(t, pages, 1)
+	assert.NotContains(t, pages[0].Content, "type:")
+	assert.Contains(t, pages[0].Content, "title: 'Basecamp'")
+}