Security audit
Security checks across malware telemetry and agentic risk
The skill appears to provide the advertised reptile video analysis, but it also creates and reuses account identity, stores tokens locally, and sends media and identifiers to cloud services with weak user-facing consent controls.
Review this skill before installing if you do not want reptile enclosure footage, supplied video URLs, account identifiers, or report history sent to the vendor cloud. Prefer installing only with an account and workspace you are comfortable linking to this service, and check whether the publisher offers explicit consent, retention, and token-storage controls.
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"):| 🔎 使用提醒 | **4 级提醒策略递进**（info → notice → important → urgent），呕吐事件直接进入 Level 4 | | 🔎 使用提醒 | 单日提醒上限：Level 1 不限 / Level 2 × 4 / Level 3 × 3 / **Level 4 × 5（呕吐每次必报，不可压制）** | | 🔎 使用提醒 | 红线约束 | | 🧑⚖️ 结果性质 | **🚨 禁止**做"隐孢子虫病 / 库道虫病 / OPMV / 蛇类传染性脑膜炎 / 肠道堵塞 / 代谢性骨病"等具体疾病诊断 | | 🔎 使用提醒 | **🚨 绝对禁止**输出具体药物名称、剂量、给药方案、灌肠剂、催吐剂、止吐药 | | 🔎 使用提醒 | **🚨 绝对禁止**输出"强制开口喂食""灌食""饥饿疗法 X 天"等具体操作剂量（任何操作必须由兽医现场判断） | | 🔎 使用提醒 | **禁止**长期存储完整爬宠箱视频（≤ 14 天，仅入库喂食事件 + 异常事件片段；养殖场按管理规定） |
--- name: "smyx-reptile-feeding-refusal-vomiting-analysis" description: "Through fixed enclosure cameras, the system analyzes feeding-time and post-feeding videos of reptiles (snakes, lizards, turtles) to detect prey-attack behavior, successful swallowing, and regurgitation (vomiting). | 通过爬宠箱固定摄像头，分析喂食时及喂食后一段时间的视频，检测爬行动物（如蛇、蜥蜴、龟）的进食行为：是否主动攻击猎物（如鼠、昆虫）、是否成功吞食、以及是否在进食后短时间内将食物吐出（反吐）。当宠物对猎物无视、逃避（拒食）或将已吞入的食物吐出时，记录异常事件并输出提示。" version: "1.0.7" license: "MIT-0" ---
VirusTotal findings are pending for this skill version.
Detected: suspicious.install_untrusted_source