visla

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly supports a /visla url command and states it "Create[s] AI-generated videos from ... web URLs" and that the url command "executes the complete flow automatically," meaning it fetches and ingests arbitrary public web pages (untrusted third‑party content) which can directly influence generation and tool actions.