lead-gen-scraper

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow is described as “Find Leads” from outsider-authored sources like LinkedIn, company websites, directories, review sites, and event attendee lists, where the agent would ingest scraped/public page text and profile/comment content into the LLM context for extraction/enrichment.