whiteboarding
Warn
Audited by Snyk on Mar 9, 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 Phase 2 "Web Research (When technology choice is involved)" explicitly instructs using WebSearch/WebFetch to gather information from the open web, so the agent will fetch and interpret untrusted third-party web content (public sites/forums) that can influence approach selection and subsequent actions.
Audit Metadata