moat-analysis

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and WebSearch public third-party sources (e.g., "Step 3 — Gather Qualitative Moat Evidence: Use WebSearch to find recent moat analyses, brand strength rankings, patent portfolios...") and to ingest SEC/XBRL and external sites for qualitative evidence, which the agent is expected to read and use to determine moat ratings—exposing it to untrusted web content that can influence decisions.