creating-video-websites
Warn
Audited by Snyk on Apr 28, 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). The mandatory "Step 0: The Interview" in SKILL.md explicitly asks "Do you have a website URL I should pull content from," requiring the agent to fetch and incorporate arbitrary public website content (untrusted third‑party pages) as part of its workflow, which can materially influence what the agent builds and how it acts.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill explicitly loads required runtime scripts from CDNs — https://cdn.jsdelivr.net/npm/lenis@1/dist/lenis.min.js, https://cdn.jsdelivr.net/npm/gsap@3/dist/gsap.min.js, and https://cdn.jsdelivr.net/npm/gsap@3/dist/ScrollTrigger.min.js — which execute remote JavaScript during runtime and are listed as required dependencies.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata