launchfast-full-research-loop

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly calls external data-fetching tools—e.g., mcp__launchfast__research_products (Phase 1 reading Amazon product/listing/review data), mcp__launchfast__supplier_research (Phase 3 querying Alibaba suppliers), and mcp__launchfast__amazon_keyword_research (Phase 4 using ASIN-derived Amazon keywords)—which ingest untrusted/public third-party content that the agent must read and use to make decisions (verdicts, supplier picks, PPC actions).