product-video

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). SKILL “product-video” ingests outsider-authored free text indirectly only when a user supplies an external target URL in actions.json, after which the required runtime drives a browser to that page and records/edits based on the page’s rendered content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The render page imports the three/mediabunny package from esm.sh at render time (mentioned as "esm.sh"), meaning remote JavaScript is fetched and executed during the skill's runtime and is a required dependency for rendering.