analyze-video

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

• Third-party content exposure detected (medium risk: 0.30). The workflow analyzes user-provided video files by extracting frames and audio transcripts, which can contain untrusted external text injected into the video or audio stream.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 0.70). The skill documents operational video generation requests via the Arcads API (POST /v2/videos/generate), which constitutes a direct financial/service operation (charges/credit usage for generation). However, the workflow relies entirely on conversational/user steps ("Show the credit cost estimate and wait for confirmation" and "Ask the user for a productId", SKILL.md:321-324) without any documented independent authentication or authorization mechanism enforced by the service or execution layer for the API route itself.