research-methodology

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly mandates using WebSearch/WebFetch and instructs opening and extracting content from public sources (see "Search Strategy" / "Source Hierarchy" and "WebSearch Patterns" which name Stack Overflow, Dev.to, GitHub and arbitrary URLs) and requires listing those URLs in the document template's sources frontmatter, so the agent will ingest untrusted, user-generated third‑party web content.