design-review
Warn
Audited by Snyk on Apr 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's instructions (SKILL.md and references/inspiration.md) explicitly tell agents to "visit 2-3 reference sites" and to research external references (e.g., Mobbin, Dribbble, Awwwards, Godly) when browser access is available, meaning the agent will fetch and interpret public, user-generated web content as part of its workflow and those pages could materially influence subsequent design decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata