social-content

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Reverse Engineering Viral Content" workflow explicitly instructs scraping and collecting public social media posts (e.g., LinkedIn, Twitter/X) using tools like Apify and PhantomBuster under the "SCRAPE — Collect Posts at Scale" step, and then requires analyzing that untrusted user-generated content to drive patterns, playbooks, and subsequent actions—constituting clear ingestion of third-party content that can influence agent behavior.