write

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2 "Research (Parallel Agents)" — specifically Agent 3 "Use Case Research" — explicitly instructs a web search to find and ingest content from public sources (official docs, GitHub discussions, technical blogs), meaning untrusted third‑party content will be read and used to influence writing and tooling decisions.