Security checks across malware telemetry and agentic risk
This data-cleaning skill appears legitimate, but it can send dataset-derived content to AI providers and Feishu despite claiming processing is local.
Review before installing. Use only with data you are authorized to share, and treat AI classification, AI field identification, Feishu output, and Pro report generation as potential external disclosure paths. Prefer local-only runs with no AI key and no Feishu modules available unless the developer adds clear opt-in prompts, redaction, and accurate privacy documentation.
},
method="POST",
)
with urllib.request.urlopen(req, timeout=20) as resp:
raw = json.loads(resp.read().decode("utf-8"))
content = raw["choices"][0]["message"]["content"]},
method="POST",
)
with urllib.request.urlopen(req, timeout=15) as resp:
raw = json.loads(resp.read().decode("utf-8"))
content = raw["choices"][0]["message"]["content"]},
data=b"{}",
)
with urllib.request.urlopen(req, timeout=10) as resp:
data = json.loads(resp.read().decode("utf-8"))
if data.get("valid", False):
result = {"valid": True, "tier": _prefix_to_tier(api_key)}No VirusTotal findings