blog-trend-researcher
Warn
Audited by Snyk on Feb 16, 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). This skill explicitly performs web searches and ingests content from public sites and user-generated sources—see "Phase 2: Multi-Source Research" (Web Search: current articles, blog posts, news; Community: forums, discussions, Q&A sites) and the parallel researcher agents—so the agent will read and interpret untrusted third-party content.
Audit Metadata