product-competitor-intelligence

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

• Third-party content exposure detected (high risk: 0.90). This skill’s workflow explicitly instructs runtime web search/extraction (“search and extract… competitor intelligence” and “extract… product, pricing… reviews, docs… official sources”), which will ingest outsider-authored free text from public competitor/retailer/marketplace pages into the agent’s LLM context.