Chain Builder
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: 1.00). The skill's example "Research → Analysis → Report Chain" includes a Stage 1 "Web Research" step that explicitly instructs the agent to use web search/web scraping to find sources and summaries (public URLs), meaning it would ingest untrusted public web content for downstream analysis.
Audit Metadata