social-media-scraper

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly instructs scalable, evasion-oriented scraping of social media using residential proxies, sticky sessions, and "expendable" accounts to harvest profiles, posts, followers, and other user data beyond API limits—facilitating unauthorized data exfiltration and abusive behavior.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to scrape public social media platforms (Instagram, TikTok, Twitter/X, YouTube, Facebook) and ingest user-generated posts, comments, profiles, and hashtag pages—untrusted third‑party content that the agent will read and use for analytics and follow-up actions.