scholar-slides

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests user-supplied paper content (PDF/arXiv/DOI) and then reads/extracts its text/figures/captions into the LLM context (Stage 1 digest creation via scripts/prepare_source.py and subsequent per-slide spec generation), which is outsider-authored free text from the paper source.