frontend-design
Warn
Audited by Snyk on Apr 7, 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.md explicitly instructs the agent to "Browse first—scan the library" and to copy install commands from public component registries (e.g., magicui.design, ui.aceternity.com, and 21st.dev) so the agent will fetch and interpret open, third‑party webpages/components as part of its workflow, which could allow those pages to influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata