transcribe

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and fetches arbitrary remote media via commands like "voxflow asr --url " (SKILL.md Quick start / Options) and the end-to-end pipelines (video-translate / publish) process those transcripts for translation/dubbing and agent orchestration, so untrusted public URLs or downloaded web videos are ingested and their content can materially influence subsequent agent actions.