x-mentor-skill-nuwa

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

• Third-party content exposure detected (high risk: 0.90). The skill's Account Diagnostics workflow explicitly describes automatic data collection via "Tier 1: Automatic via computer-use / browser tools" and stores/reads tweets_{date}.json and profile data from user-data/{username}/, which indicates it fetches and ingests public, user-generated X (Twitter) content that the agent will read and use to drive recommendations.