list-building

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content explicitly instructs large-scale scraping/harvesting of personal contact data and orchestration of 100K+ cold outreach campaigns (including tools and techniques to bypass provider limits), which enables data exfiltration and mass unsolicited outreach/abuse.

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

• Third-party content exposure detected (high risk: 0.78). At runtime the required workflow can ingest outsider-authored free text when it “visit[s] this website /company_domain” to produce /company_summary (step 5 in resources/templates/beginner-workflow.md), and that scraped page text comes from arbitrary third-party websites (web content category).