web-fetch

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

• Third-party content exposure detected (high risk: 1.00). The skill fetches and returns extracted content from arbitrary user-provided URLs by calling the Jina Reader API (API_BASE_URL = "https://r.jina.ai" with the encoded URL in scripts/web_fetch.py), so it ingests untrusted third-party web content that could contain indirect prompt injections.