content-rendering
Warn
Audited by Snyk on Apr 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly renders HTML coming from CMSs, APIs, translations and user-generated content (see "When to Use This Skill" and examples like UpsellNudgeButton: dynamic HTML from API, Sustainability: CMS content, and EmptyState: translated HTML in SKILL.md / references/examples.md), so untrusted third‑party text/links are ingested and displayed (and can trigger link-open actions), allowing adversarial content to influence behavior beyond mere display.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata