Rdk X5 Ai Detect

在 RDK X5 的 10TOPS BPU 上运行单个 AI 推理算法：YOLO 目标检测、图像分类、语义分割、人脸识别、手势识别、人体关键点、开放词汇检测（DOSOD/YOLO-World）、双目深度估计、语音识别、端侧轻量 LLM（≤2B 参数量化模型）。Use when the user wants to...

This skill appears internally consistent for running AI inference on an RDK X5 device. Before installing/using it: (1) confirm you are on the intended RDK X5 hardware with TROS/ROS2 installed; (2) avoid running the provided pip commands without verifying the packages' source (they may fetch code from the network); (3) do not embed credentials in command lines—use protected config files or environment variables and be aware such command lines can leak to process lists or shell history; (4) the web UI (port 8000) and RTSP streams expose video data—ensure network access is restricted and authenticated; (5) verify model .bin files are from trusted sources and correctly converted (hb_mapper); and (6) if you need camera setup, media encoding, or model conversion, use the skill names referenced in the doc (rdk-x5-camera, rdk-x5-media, Horizon toolchain) rather than this skill. If you want a deeper safety check, provide the origin of the hobot-* packages, the TROS setup.bash contents, or the network endpoints used by the device.

Type: OpenClaw Skill Name: rdk-x5-ai-detect Version: 1.0.0 The skill bundle provides standard technical instructions and ROS2 commands for performing AI inference on the RDK X5 hardware platform. It includes legitimate setup steps such as installing hardware-specific Python libraries (hobot-dnn-rdkx5) and monitoring BPU usage via sysfs, with no evidence of malicious intent, data exfiltration, or prompt injection attacks.