Security audit
Security checks across malware telemetry and agentic risk
This skill performs the advertised cloud health screening, but it also silently creates and persists identity tokens while handling sensitive face and health data.
Review before installing. This skill sends uploaded face images/videos or provided media URLs to a remote service, queries cloud health-report history, creates or reuses an internal identity, and stores authentication tokens locally. It should only be used where users have clearly consented to cloud processing of biometric and health-related data and understand that results are screening-only, not medical diagnosis.
if filters:
for key, value in filters.items():
query = query.filter(getattr(self.__model__, key) == value)
if offset:
query = query.offset(offset)if filters:
for key, value in filters.items():
query = query.filter(getattr(self.__model__, key) == value)
return query.scalar()
finally:"source": ConstantEnum.DEFAULT__SKILL_HUB_NAME
}
try:
_response = requests.post(_url, json=_data)
if _response.status_code == 200:
_response_json = _response.json()
if _response_json and _response_json.get("success"):|---|---| | 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 | | 📁 格式支持 | 支持格式：jpg/jpeg/png/mp4/avi/mov，视频推荐时长 10-30 秒，最大 10MB | | 🧑⚖️ 结果性质 | **⚠️ 重要声明**：本分析结果仅供早期风险筛查参考，**不替代专业医疗诊断和检查**，发现高风险请及时到医院就诊 | | 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 | | 🌐 网络地址 | 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载 | | 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段 作为超链接地址，且自动转化为如下 Markdown |
--- name: "contactless-health-risk-detection-analysis" description: "Combines frontal facial image capture with multimodal physiological feature analysis to provide early risk screening and alerts for chronic and acute conditions such as heart attack, stroke, hypertension, and hyperlipidemia. | 非接触式健康风险识别技能，通过正面人像采集结合多模态生理特征分析，提供心梗、脑梗、高血压、高血脂等慢病急症早期风险筛查预警" version: "1.0.13" license: "MIT-0" ---
VirusTotal findings are pending for this skill version.
Detected: suspicious.install_untrusted_source