python-executor

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly enables and demonstrates fetching and parsing arbitrary public web content (e.g., the Web Scraping example using requests.get("https://example.com") and the listed libraries requests/BeautifulSoup/Selenium), so the agent can ingest untrusted third‑party pages and act on their contents, enabling indirect prompt injection.