user-model-builder
Warn
Audited by Snyk on May 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and README explicitly instruct the agent to scrape and ingest public, user-generated content from open web sources (Phase 3: "Content Scraping" — Substack via Firecrawl, Twitter via Jina, Wayback CDX for dead domains, LinkedIn exports) and Phase 4 requires reading the entire archived corpus to drive voice analysis and dossier generation, meaning untrusted third-party content is read and used to influence downstream actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata