ln-51-opportunity-evaluator

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow explicitly requires “Web research… marketplace data, communities, reviews, ads, directories, and primary customer evidence” (outsider-authored public web content) to be ingested as LLM-readable evidence during steps 2–5, creating an indirect prompt-injection risk from those external pages/messages.