Trio Stream Vision

Analyze any YouTube livestream or RTSP camera feed using natural language — ask what's happening, detect specific events, or get periodic summaries. Powered...

This skill is coherent with its description: it sends stream URLs/frames to Trio's cloud API and requires a TRIO_API_KEY. Before installing, consider: 1) privacy — frames/clips from your cameras will be uploaded to a third party (machinefi/trio); do not point it at cameras you don't own or at people without consent; 2) webhook recipients — if you configure a webhook, that endpoint will receive event data (and optionally frames); ensure you control/trust it; 3) key handling — store TRIO_API_KEY securely (not in shared scripts or public repos), rotate it if exposed, and prefer a key with limited scope if the provider supports it; 4) cost/control — continuous monitoring incurs per-minute charges, so limit durations/intervals and warn users before starting long monitors; 5) vet the provider — confirm you trust machinefi/trio for handling sensitive visual data. If you want stronger guarantees, ask the publisher for an on-prem or self-hosted option or more explicit documentation about data retention and access controls from Trio.

Type: OpenClaw Skill Name: trio-stream-vision Version: 1.0.0 The trio-stream-vision skill is a legitimate integration for the Trio Vision API, designed to analyze live video streams (YouTube, RTSP, HLS) using natural language. It utilizes standard system tools like curl and python3 to interact with the trio.machinefi.com API and includes explicit instructions in SKILL.md to prevent the leakage of the TRIO_API_KEY. No evidence of malicious intent, data exfiltration, or unauthorized command execution was found in the code or the extensive documentation provided.