carousel-designer
Warn
Audited by Snyk on Mar 3, 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's required Phase 1 explicitly tells the agent to read references/REFERENCES.md and extract layout/type/color patterns, and that file explicitly accepts/prescribes pasting URLs to LinkedIn carousels, raw HTML/CSS, and screenshots from public sites—untrusted third‑party content that the agent must interpret and that will materially drive layout and rendering decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill's HTML loads the Tailwind CDN script at runtime (https://cdn.tailwindcss.com), which fetches and executes remote JavaScript in the rendering context and is a required dependency for correct rendering, so it constitutes a runtime external resource that executes remote code.
Audit Metadata