link-prospect-qualification

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

• Third-party content exposure detected (high risk: 0.75). The workflow’s runtime path ingests “raw prospect list with source evidence when available” and then (in Step 4) “manually review[s] … outbound-link motivation, recency, design, ads, text quality, contact path,” which in practice typically requires fetching/reading outsider-authored page text from the provided prospect URLs (public web content) into the agent’s LLM context for evaluation.