rating-prompt-strategy

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Recovering from a Rating Drop" diagnosis explicitly instructs the agent to "Read the 1-star reviews for that period" (user-generated App Store/Play Store reviews), which requires ingesting untrusted public third-party content that can influence diagnosis and next actions.