design

Warn

Audited by Snyk on Apr 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: 0.90). The SKILL.md "Process" and the references (e.g., "Research Prior Art" in SKILL.md and the prior-art lists in references/components.md and references/features.md) explicitly require consulting public third‑party sites (Base UI, WAI‑ARIA APG, Media Chrome, Vidstack, Video.js, Plyr), so the agent is expected to fetch/read untrusted external web content as part of its required workflow and that content could materially influence design decisions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 9, 2026, 06:31 AM
Issues
1