playbook-linkedin-engagement

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This playbook explicitly instructs harvesting LinkedIn engagers, running email-finding and enrichment, and exporting those people as prospect rows (with automated pushes to client DNC lists) — a deliberate, targeted data-extraction workflow that enables non-consensual collection and downstream outreach of personal contact data.

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

• Third-party content exposure detected (low risk: 0.10). Exclusion: the required workflow ingests only operator-provided configuration (source URLs/domains, client domain, ICP) and scraped LinkedIn post/reaction/comment data that it windowed/shortlisted by engagement count, rather than ingesting arbitrary outsider-authored free text selected without first targeting specific LinkedIn posts/accounts.