study-exemplars

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text is ingested when the skill fetches and parses each exemplar paper’s OA copy (e.g., via fetch-paper/resolve_oa.py and then reading the PDF/HTML text) from external sources at runtime; that paper text is not authored by the operating user and is fed into the agent’s LLM context for analysis.