virlo

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the skill calls Virlo’s API endpoints (e.g., GET /v1/comet/:id/videos in cmd_videos), and in --json mode it passes the returned outsider-authored video descriptions/hashtags (from TikTok/Instagram/YouTube) into an LLM-readable JSON context via echo "$response" | python3 ... (and then onward to downstream pipeline steps).