paper-analysis-assistant

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow downloads PDFs from arXiv (scripts/download_pdf.py as described in SKILL.md) and extracts and processes the paper text (scripts/extract_text.py, generate_html.py, plus agent "智能体步骤" for generating dialogue/summary), meaning untrusted public arXiv content is ingested and directly read by the agent and can influence subsequent generation/decisions.