read-web-scraper

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow fetches runtime web page content from a user-supplied URL (public web content) and converts/prints the resulting HTML text into markdown via scripts/fetch_url.py (requests.get/urlopen → parser.feed(html_content) → print(content)), which would be ingested into the agent’s LLM context as free text.