grand-slam-offer

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 Step 1 explicitly instructs the agent to run web_search to research "[product name] features pricing review" and gather features, pricing, reviews, and competitors from public web pages—untrusted third-party content that the agent must read and use to score the Value Equation and design the offer, allowing indirect instructions to influence actions.