best-practice-first

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory Research Phase explicitly requires using WebSearch/WebFetch to fetch and read public web pages (e.g., "Step 2: Search Official Documentation" and "Step 4: Search for Pitfalls" in Phase 1), meaning the agent will ingest and act on untrusted third‑party web content that can influence decisions and tool use.