generate-voice-guide

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly directs the agent to scrape and ingest user-generated public social content (Phase 1: use Apify actor "apidojo/twitter-user-tweets-scraper" for X and "harvestapi/linkedin-profile-posts" for LinkedIn) and to analyze and quote those posts as core inputs for generating guides and iteratively influencing outputs, so untrusted third‑party content can change agent behavior.