tencentcloud-faceid-analyzedenselandmarks

腾讯云稠密人脸关键点(AnalyzeDenseLandmarks)接口调用技能。当用户需要对人脸图片进行稠密关键点定位时，应使用此技能。可返回人脸框坐标，以及人脸各部位（眼睛、眉毛、嘴巴、鼻子、瞳孔、中轴线、下巴、眼袋、额头）的稠密轮廓关键点坐标。支持图片Base64和图片URL两种输入方式。

This skill sends images (via URL or Base64) and your Tencent Cloud API credentials to Tencent Cloud's IAI endpoint (iai.tencentcloudapi.com) to perform dense face-landmark detection — that is exactly its purpose. Before installing/providing credentials: 1) Only use with a Tencent Cloud account you control and rotate the credentials if they are shared; 2) Avoid sending sensitive/private images unless you accept they will be processed by Tencent Cloud; 3) Verify you install the official tencentcloud-sdk-python package (pip) from PyPI and review network policies if you need to restrict outbound calls; 4) Monitor Tencent Cloud audit logs for API usage; 5) If you need offline or local processing, this skill is not suitable because it depends on Tencent's cloud API.

Type: OpenClaw Skill Name: tencentcloud-faceid-analyzedenselandmarks Version: 1.0.0 The skill bundle is a legitimate implementation for calling the Tencent Cloud FaceID AnalyzeDenseLandmarks API. The Python script (scripts/main.py) uses the official tencentcloud-sdk-python to process images via local file paths or URLs, correctly handling authentication through environment variables and implementing standard size limits. No evidence of data exfiltration, malicious code execution, or prompt injection was found.