Security audit
Security checks across malware telemetry and agentic risk
The skill can generate manufacturing consulting reports, but it also automatically processes uploads, scans other local skills, rewrites its own instructions, stores logs, and pushes files externally without enough user control.
Review before installing. Use only in a controlled workspace, and disable or require explicit confirmation for automatic upload processing, local skill scanning, self-repair writes to SKILL.md, persistent logs, web searches, non-local Ollama endpoints, and WeChat/QQ/Tencent delivery. Treat factory photos, production metrics, customer files, and generated reports as confidential unless the user approves each extraction and transfer.
try:
import urllib.request
req = urllib.request.Request(f"{OLLAMA_HOST}/api/tags")
with urllib.request.urlopen(req, timeout=5) as resp:
data = json.loads(resp.read())
return len(data.get("models", [])) > 0
except:)
try:
with urllib.request.urlopen(req, timeout=120) as resp:
data = json.loads(resp.read())
return data.get("response", "")
except Exception as e:64/64 vendors flagged this skill as clean.
No suspicious patterns detected.