podcast-production

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs running web-search sub-agents to collect public social media handles (Step 0.5 "Guest Social Research") and to perform YouTube outlier research (Step 1.5 and repeated "always run /yt-outlier"), ingesting open/public user-generated content which is then used to weight title frameworks, inform clip selection, and drive downstream decisions—meeting the criteria for untrusted third-party content that can influence agent behavior.