fix(viewer): harden PDF report rendering

pyproject.toml

@@ -43,6 +43,7 @@ dependencies = [
   "requests>=2.32.0",
   "cvss>=3.2",
   "caido-sdk-client>=0.2.0",
+  "markdown-it-py>=3.0.0",
   "reportlab>=4.0",
   "pypdf>=5.0",
   # Cap <49: 49.x drops the universal2 macOS wheel (arm64-only), which breaks

strix/interface/viewer/report_pdf.py

@@ -20,6 +20,7 @@
 from io import BytesIO
 from typing import TYPE_CHECKING, Any
 
+from markdown_it import MarkdownIt
 from pypdf import PdfReader, PdfWriter
 from reportlab.lib import colors
 from reportlab.lib.enums import TA_CENTER
@@ -49,6 +50,8 @@
 if TYPE_CHECKING:
     from pathlib import Path
 
+    from markdown_it.token import Token
+
 
 # Palette lifted from the cloud report theme (styles/base.ts, docx/theme.ts).
 _INK = colors.HexColor("#000000")
@@ -72,11 +75,21 @@
 _MONO = "Courier"
 
 _PAGE_W, _PAGE_H = A4
+_INLINE_MD = MarkdownIt("commonmark", {"html": False, "linkify": False}).disable(
+    ["autolink", "image", "link"]
+)
+_UNSAFE_TEXT_RE = re.compile(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\x9f\ud800-\udfff\ufffe\uffff]")
+
+
+def _normalize_text(value: Any) -> str:
+    """Normalize characters that ReportLab cannot safely serialize."""
+    text = str(value).replace("\r\n", "\n").replace("\r", "\n")
+    return _UNSAFE_TEXT_RE.sub("\ufffd", text)
 
 
 def _esc(value: Any) -> str:
     """Escape a value for reportlab's Paragraph markup."""
-    return html.escape(str(value)).replace("\n", "<br/>")
+    return html.escape(_normalize_text(value)).replace("\n", "<br/>")
 
 
 class _NumberedCanvas(pdfcanvas.Canvas):  # type: ignore[misc]  # reportlab base is untyped
@@ -253,7 +266,10 @@ def _duration(start: Any, end: Any) -> str:
     end_dt = _parse_time(end)
     if not start_dt or not end_dt:
         return "n/a"
-    seconds = int((end_dt - start_dt).total_seconds())
+    try:
+        seconds = int((end_dt - start_dt).total_seconds())
+    except (OverflowError, TypeError):
+        return "n/a"
     if seconds < 0:
         return "n/a"
     hours, remainder = divmod(seconds, 3600)
@@ -265,10 +281,18 @@ def _duration(start: Any, end: Any) -> str:
     return f"{secs}s"
 
 
-def _severity_badge(styles: dict[str, ParagraphStyle], severity: str) -> Table:
+def _normalize_severity(value: Any) -> str:
+    severity = str(value or "").lower().strip()
+    if severity == "informational":
+        return "info"
+    return severity if severity in {*_SEVERITY_COLORS, "info"} else "low"
+
+
+def _severity_badge(styles: dict[str, ParagraphStyle], severity: Any) -> Table:
     """A colored pill matching .severity-badge in the cloud report."""
+    severity = _normalize_severity(severity)
     color = _SEVERITY_COLORS.get(severity, _MUTED)
-    cell = Paragraph(severity.upper(), styles["badge"])
+    cell = Paragraph(_esc(severity.upper()), styles["badge"])
     table = Table([[cell]], colWidths=[len(severity) * 6.5 + 20])
     table.setStyle(
         TableStyle(
@@ -406,27 +430,36 @@ def _cover(
 
 
 def _inline_md(text: str) -> str:
-    """Convert inline markdown (bold, italic, `code`) to reportlab markup.
-
-    Code spans are stashed as placeholders before bold/italic run, so bold that
-    wraps a code span (``**`x`**``) works and code contents are never mangled.
-    """
-    codes: list[str] = []
-
-    def _stash(match: re.Match[str]) -> str:
-        codes.append(match.group(1))
-        return f"\x00{len(codes) - 1}\x00"
-
-    seg = html.escape(re.sub(r"`([^`]+)`", _stash, text))
-    seg = re.sub(r"\*\*(.+?)\*\*", r"<b>\1</b>", seg)
-    seg = re.sub(r"__(.+?)__", r"<b>\1</b>", seg)
-    seg = re.sub(r"\*(.+?)\*", r"<i>\1</i>", seg)
-
-    def _restore(match: re.Match[str]) -> str:
-        inner = html.escape(codes[int(match.group(1))])
-        return f'<font face="{_MONO}" color="#b31d28">{inner}</font>'
-
-    return re.sub(r"\x00(\d+)\x00", _restore, seg)
+    """Render a safe subset of inline Markdown as ReportLab markup."""
+    tokens = _INLINE_MD.parseInline(_normalize_text(text))[0].children or []
+    return "".join(_inline_token_markup(token) for token in tokens)
+
+
+def _inline_token_markup(token: Token) -> str:
+    fixed_markup = {
+        "strong_open": "<b>",
+        "strong_close": "</b>",
+        "em_open": "<i>",
+        "em_close": "</i>",
+        "hardbreak": "<br/>",
+        "softbreak": " ",
+    }.get(token.type)
+    if fixed_markup is not None:
+        return fixed_markup
+    if token.type == "code_inline":
+        return f'<font face="{_MONO}" color="#b31d28">{html.escape(token.content)}</font>'
+    # Unsupported token content remains escaped so parser extensions cannot
+    # expose ReportLab tags.
+    return html.escape(token.content)
+
+
+def _markdown_paragraph(text: str, style: ParagraphStyle) -> Paragraph:
+    """Build a Markdown paragraph, falling back to escaped source text."""
+    source = _normalize_text(text)
+    try:
+        return Paragraph(_inline_md(source), style)
+    except ValueError:
+        return Paragraph(_esc(source), style)
 
 
 def _strip_leading_heading(md: str) -> str:
@@ -447,12 +480,12 @@ def _markdown_flowables(  # noqa: PLR0915 - cohesive block parser, splitting hur
 
     def flush_para() -> None:
         if para:
-            flow.append(Paragraph(_inline_md(" ".join(para)), styles["body"]))
+            flow.append(_markdown_paragraph(" ".join(para), styles["body"]))
             para.clear()
 
     def flush_bullets() -> None:
         for marker, item in bullets:
-            flow.append(Paragraph(f"{marker}&nbsp;{_inline_md(item)}", styles["bullet"]))
+            flow.append(_markdown_paragraph(f"{marker}\u00a0{item}", styles["bullet"]))
         bullets.clear()
 
     lines = md.replace("\r\n", "\n").split("\n")
@@ -479,7 +512,7 @@ def flush_bullets() -> None:
         if heading:
             flush_para()
             flush_bullets()
-            flow.append(Paragraph(_inline_md(heading.group(2)), styles["md_heading"]))
+            flow.append(_markdown_paragraph(heading.group(2), styles["md_heading"]))
             i += 1
             continue
         ordered = re.match(r"^(\d+)\.\s+(.*)$", stripped)
@@ -532,7 +565,7 @@ def _finding_flowables(
     styles: dict[str, ParagraphStyle], index: int, vuln: dict[str, Any]
 ) -> list[Flowable]:
     title = vuln.get("title") or "Untitled finding"
-    severity = str(vuln.get("severity") or "").lower().strip() or "low"
+    severity = _normalize_severity(vuln.get("severity"))
 
     meta_bits = []
     if vuln.get("cvss") is not None:

tests/test_report_pdf.py

@@ -4,13 +4,19 @@
 
 import json
 from io import BytesIO
+from itertools import product
 from typing import TYPE_CHECKING
 
 import pytest
 from pypdf import PdfReader
 from pypdf.errors import WrongPasswordError
+from reportlab.lib.styles import ParagraphStyle
+from reportlab.platypus import Paragraph
 
 from strix.interface.viewer.report_pdf import (
+    _duration,
+    _inline_md,
+    _normalize_severity,
     build_encrypted_report,
     encrypt_pdf,
     generate_password,
@@ -60,6 +66,10 @@ def _make_run(base: Path, name: str = "sample") -> Path:
     return run_dir
 
 
+def _pdf_text(pdf: bytes) -> str:
+    return "\n".join(page.extract_text() or "" for page in PdfReader(BytesIO(pdf)).pages)
+
+
 def test_generate_report_pdf_has_pdf_header(tmp_path: Path) -> None:
     run_dir = _make_run(tmp_path)
     pdf = generate_report_pdf(run_dir)
@@ -103,3 +113,132 @@ def test_build_encrypted_report(tmp_path: Path) -> None:
     reader = PdfReader(BytesIO(pdf_bytes))
     assert reader.is_encrypted
     assert reader.decrypt(password)
+
+
+@pytest.mark.parametrize(
+    ("text", "expected"),
+    [
+        ("**bold**", "<b>bold</b>"),
+        ("__bold__", "<b>bold</b>"),
+        ("*italic*", "<i>italic</i>"),
+        ("***both***", "<i><b>both</b></i>"),
+        ("**bold with *italic* inside**", "<b>bold with <i>italic</i> inside</b>"),
+        ("*outer **bold** inner*", "<i>outer <b>bold</b> inner</i>"),
+        (r"\*literal\*", "*literal*"),
+        ("******", "******"),
+        ("`a * < &`", '<font face="Courier" color="#b31d28">a * &lt; &amp;</font>'),
+        (
+            "![alt](https://example.invalid/image.png)",
+            "![alt](https://example.invalid/image.png)",
+        ),
+        ("<https://example.invalid>", "&lt;https://example.invalid&gt;"),
+    ],
+)
+def test_inline_md_emits_only_safe_balanced_markup(text: str, expected: str) -> None:
+    markup = _inline_md(text)
+    assert markup == expected
+    Paragraph(markup, ParagraphStyle("test"))
+
+
+@pytest.mark.parametrize(
+    "text",
+    [
+        "*a **b* c**",
+        "**a *b** c*",
+        "*outer **inner* end**",
+        "__a *b__ c*",
+        "***__***__",
+        "__***__***",
+        "<b><i></b></i>",
+        "<font size='999'>x</font>",
+        "<img src='/definitely/missing.png'/>",
+        "\x000\x00 `code` \x0099\x00",
+        "\ud800",
+    ],
+)
+def test_inline_md_survives_malformed_external_text(text: str) -> None:
+    markup = _inline_md(text)
+    assert "\x00" not in markup
+    assert "\ud800" not in markup
+    Paragraph(markup, ParagraphStyle("test"))
+
+
+def test_inline_md_generated_corpus_never_breaks_reportlab() -> None:
+    style = ParagraphStyle("test")
+    for length in range(1, 6):
+        for chars in product("*_`a ", repeat=length):
+            Paragraph(_inline_md("".join(chars)), style)
+
+
+def test_generate_report_pdf_survives_hostile_run_fields(tmp_path: Path) -> None:
+    run_dir = _make_run(tmp_path)
+    hostile = "****** <b><i></b></i> <img src='/definitely/missing.png'/> \x000\x00 \ud800"
+    record = json.loads((run_dir / "run.json").read_text(encoding="utf-8"))
+    record.update(
+        {
+            "run_name": hostile,
+            "targets_info": [{"original": hostile}],
+            "scan_mode": hostile,
+            "status": hostile,
+            "start_time": hostile,
+            "end_time": hostile,
+            "scan_results": {
+                "executive_summary": hostile,
+                "methodology": hostile,
+                "technical_analysis": hostile,
+                "recommendations": hostile,
+            },
+        }
+    )
+    (run_dir / "run.json").write_text(json.dumps(record), encoding="utf-8")
+
+    text = _pdf_text(generate_report_pdf(run_dir))
+    assert "******" in text
+    assert "<b><i></b></i>" in text
+    assert "<img src='/definitely/missing.png'/>" in text
+
+
+def test_generate_report_pdf_survives_hostile_finding_fields(tmp_path: Path) -> None:
+    run_dir = _make_run(tmp_path)
+    hostile = "****** <b><i></b></i> <img src='/definitely/missing.png'/> \x000\x00 \ud800"
+    vulnerability = {
+        "title": hostile,
+        "severity": hostile,
+        "cvss": hostile,
+        "description": hostile,
+        "impact": hostile,
+        "technical_analysis": hostile,
+        "poc_description": hostile,
+        "poc_script_code": hostile,
+        "evidence": hostile,
+        "remediation_steps": [hostile],
+        "target": hostile,
+        "endpoint": hostile,
+        "method": hostile,
+    }
+    (run_dir / "vulnerabilities.json").write_text(json.dumps([vulnerability]), encoding="utf-8")
+
+    text = _pdf_text(generate_report_pdf(run_dir))
+    assert "******" in text
+    assert "<b><i></b></i>" in text
+    assert "<img src='/definitely/missing.png'/>" in text
+    assert text.count("LOW") == 2  # severity grid label plus canonicalized finding badge
+
+
+@pytest.mark.parametrize(
+    ("value", "expected"),
+    [
+        ("CRITICAL", "critical"),
+        (" info ", "info"),
+        ("informational", "info"),
+        ("<b><i></b></i>", "low"),
+        ({"severity": "critical"}, "low"),
+        (None, "low"),
+    ],
+)
+def test_normalize_severity_restricts_badge_markup(value: object, expected: str) -> None:
+    assert _normalize_severity(value) == expected
+
+
+def test_duration_rejects_mixed_timezone_awareness() -> None:
+    assert _duration("2026-01-01T00:00:00", "2026-01-01T01:00:00Z") == "n/a"