duoshe

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

• Third-party content exposure detected (high risk: 0.90). Flagged because SKILL.md's "Accepted Inputs" and "Source Handling" explicitly require fetching and analyzing open third‑party resources (paper PDFs, arXiv/publisher pages, author project pages, Semantic Scholar/OpenAlex/Google Scholar metadata), which the agent is expected to read and use to drive research decisions and follow‑on actions.