Trio Vision

Turn any live camera into a smart camera — describe what to watch for in plain English, get alerts in your chat when it happens. Ask questions about any live...

This skill appears to do what it says: it wraps a third‑party Vision API and needs a single API key. Before installing, confirm you trust Trio/machinefi (https://trio.machinefi.com) because using the skill will send frames/clips and stream URLs to their servers. Be cautious with private RTSP/local URLs (they may expose your LAN streams) and with the include_frame option or webhooks — these can deliver image data to external endpoints. Use a scoped or rotateable API key if possible, do not paste the key publicly, review Trio's privacy policy, and test first with non‑sensitive streams. Also verify expected costs (monitoring is billed per minute) and ensure any webhook endpoints you provide are trusted. If you want, I can show the exact curl calls the skill will run or help draft a safer test workflow (short runs, low-resolution frames, no include_frame) to validate functionality without exposing sensitive video.

Type: OpenClaw Skill Name: trio-vision Version: 1.0.0 The trio-vision skill bundle is a legitimate integration for the Trio Vision AI API, allowing agents to analyze live video streams (YouTube, Twitch, RTSP) using natural language. The bundle is well-documented, including a SKILL.md with clear operational rules, a first-principles analysis, and an implementation guide that even suggests a more secure JavaScript-based alternative. While the use of curl templates in SKILL.md poses a theoretical shell injection risk if the agent fails to sanitize user-provided URLs, there is no evidence of malicious intent; rather, the instructions include security-positive directives such as explicitly forbidding the logging of API keys and requiring cost disclosures to users.