koriigami-write-article

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

• Third-party content exposure detected (high risk: 0.80). The skill's Step 2 "Research" explicitly requires performing web searches and "Collect 10-20 high-quality sources with URLs" and the Citation Rules demand embedding inline hyperlinks to those public URLs, so the agent will fetch and ingest open/public third‑party content (websites, journals, reports) as part of its workflow.