recoup-catalog-review-deal

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via the deal workspace’s source/ files (e.g., seller-provided .txt/.md/.html/.pdf content) that are ingested/parsed into human-readable findings/memos (including findings/findings.json and memos/*), which the agent then uses to write the customer-facing dashboard and reports.