Security audit
Security checks across malware telemetry and agentic risk
The skill is a plausible cloud-based hydroponic image analysis tool, but it silently creates or reuses an identity, stores tokens locally, and sends files or report queries to external APIs.
Install only if you are comfortable with cloud processing of plant media, automatic account association, local credential/token storage, and cloud history-report retrieval. Prefer a version that explicitly discloses destinations, retention, authentication behavior, and gives the user control before uploads or report-history queries.
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 | 输入要求：支持 jpg/png 图像或 mp4/avi/mov 视频，最大 10MB；建议根部与叶部分别拍摄 | | 🧑⚖️ 结果性质 | 评估结果仅供水培养护参考，严重过浓/严重过稀建议立即换液并观察 24 小时 | | 🚫 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 | 传入的网络地址参数，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 |
VirusTotal findings are pending for this skill version.
Detected: suspicious.install_untrusted_source