longbridge-buffett-moat-stock-screener

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (SKILL.md §Workflow step 4 and "WebSearch fallback") explicitly instructs the agent to fetch and incorporate public WebSearch hits (publisher + URL + access date) — e.g., industry outlook, brand/pricing signals, Buffett 13F filings and management track records — and to use those web-sourced items in Layer-2 scoring and verdicts, which clearly exposes the agent to untrusted third-party web content that can influence decisions.