signal-scanner

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public, user-generated LinkedIn content and job postings via Apify (see SKILL.md and scripts/signal_scanner.py — functions scan_linkedin_content, scan_job_postings, and scan_profile_changes call Apify actors like harvestapi/linkedin-profile-posts and harvestapi~linkedin-job-search and then parse post_text/job data), and those third-party texts are scored and used to create signals that can change lead_status and drive downstream actions.