Security checks across malware telemetry and agentic risk
This health-report skill does what it claims, but it handles sensitive health data and has default AI/search/outbound paths that deserve careful review before installation.
Install only if you are comfortable with health records being used in AI prompts and potentially sent to configured messaging platforms and Tavily/OpenClaw agent workflows. Use a dedicated MEMORY_DIR, avoid public REPORT_BASE_URL exposure for private PDFs, configure only the outbound channels you truly need, rotate webhook/bot/API keys, and review generated logs/reports for sensitive content.
for attempt in range(3):
try:
result = subprocess.run(
['openclaw', 'agent', '--local', '--to', '+860000000000', '--message', prompt],
capture_output=True, text=True, timeout=90,
env={**os.environ, 'SYSTEM_PROMPT': '你是一位专业的私人营养师，专门服务胆结石患者。'}for attempt in range(3):
try:
result = subprocess.run(
['openclaw', 'agent', '--local', '--to', '+860000000000', '--message', prompt],
capture_output=True, text=True, timeout=90,
env={**os.environ, 'SYSTEM_PROMPT': '你是一位专业的私人营养师。输出纯 JSON，不要其他文字。'}"max_results": max_results
}).encode('utf-8')
req = urllib.request.Request(url, data=data, headers={'Content-Type': 'application/json'})
resp = urllib.request.urlopen(req, timeout=60)
result = json.loads(resp.read().decode('utf-8'))
return result.get('results', [])
except Exception as e:# 安装：pip install -r requirements.txt # PDF 生成 reportlab>=4.0.0 Pillow>=10.0.0 # 可选依赖（用于高级功能）
# PDF 生成 reportlab>=4.0.0 Pillow>=10.0.0 # 可选依赖（用于高级功能） # requests>=2.31.0 # HTTP 请求（如需网络功能）
66/66 vendors flagged this skill as clean.