niche-signal-discovery

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests open web content via Deepline enrichment (SKILL.md Step 2: exa_search with contents and crustdata_job_listings) and the analysis script (scripts/analyze_signals.py) parses dl_full_result website pages and job listings to drive lift scores and reporting, so third‑party website/job-post content can directly influence decisions and tooling.