longbridge-buffett-moat-analyzer

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs using WebSearch as a fallback for industry outlook, brand/pricing signals, management qualitative signals, regulatory news, and latest insider transactions (see "WebSearch fallback" and the Data Source Appendix rows in SKILL.md), so it fetches and ingests untrusted public web content that the agent must read and which can materially affect scoring and actions.