abundance_every_year_market_notes

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 calls scripts/fetch_market_data.py to fetch market data and up to 20 "热门财经资讯" from public third‑party news sources (财联社, 东方财富, CCTV, 新浪, 腾讯, Wind, etc.) as shown in SKILL.md and references/step1.md, and the agent is explicitly instructed to read and use those fetched, untrusted web/news contents to generate analysis and drive subsequent writing and HTML generation, creating a clear risk of indirect prompt injection.