logo-design
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Skill.md’s runtime workflow loads first-party user-authored SVG preview data by copying assets/preview.html and then reading window.VARIANTS from project-local variants.js (user-controlled free text/paths rendered by the page), creating an indirect prompt-injection-style risk if an LLM later ingests that content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata