chunked-discovery
Warn
Audited by Snyk on Apr 29, 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 performs WebSearch/WebFetch (see "Derive segments" and the Guardrails note about
--auto-drillbeing "bulk WebSearch + WebFetch") to ingest public web content (landscapes, market maps, VC theses, analyst reports) and then synthesizes segments and drives drilling/actions from that content, so untrusted third‑party pages can materially influence tool behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata