buffett-oracle-analyzer

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 explicitly instructs the agent to fetch and ingest open/public third‑party content (e.g., "信息采集" in SKILL.md: "搜索最新财报、电话会记录、重大新闻、卖方研报") and the docs/scripts (docs/data-sources.md and scripts/data_fetcher.py) integrate public sources such as Yahoo Finance, SEC EDGAR, news and transcripts which the agent is expected to read and use to drive valuation and action decisions—therefore it clearly consumes untrusted third‑party content that can influence behavior.