guest-contributor-article
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly requires collecting and reading public third‑party content (Phase 2: "Collect 3-5 pieces... Read them" including blog posts, podcasts, YouTube transcripts, and social media like LinkedIn/X) and lists scraping tools (youtube-downloader, twitter-scraper) so those untrusted user-generated sources are ingested and directly drive voice analysis, source-mapped outlines, and drafting decisions.
Audit Metadata