revai

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly allows submitting publicly accessible media URLs via "Submit Transcription Job" and retrieving their transcripts with "Get Transcript" (and proxying requests through Membrane/Rev.ai), so untrusted, user-generated third‑party content can be ingested and influence agent actions.