aesthetic-guide
Warn
Audited by Snyk on Feb 20, 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.md workflow (step 3 "Research if needed") and the Research Protocol explicitly require conducting web research and looking at open-source implementations/CodePen/public design docs to extract CSS and fonts, which means the agent will fetch and interpret untrusted public third-party content (websites, user-generated examples) as part of its required workflow.
Audit Metadata