fundamental-report-detailed

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public third-party data (e.g., Step 0 ticker resolution fetching company metadata, Step 1’s "sec-filing-reader", and "Source Links" plus the referenced data-sources.md) and requires the agent to read and use that external content to drive analysis and decisions, exposing it to untrusted web content that could carry indirect prompt injection.