Security audit
Security checks across malware telemetry and agentic risk
The skill mostly does the advertised posture-analysis job, but it also sends sensitive media and identity data to remote services and stores local auth tokens without enough user-facing control or disclosure.
Review before installing. Use this only if you are comfortable sending local videos, image/video URLs, generated or existing user identifiers, tenant/platform metadata, and report history queries to the configured remote service. Check and change the packaged dev/private endpoints, avoid passing secrets on the command line, and obtain consent before analyzing footage of identifiable people.
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"):VirusTotal findings are pending for this skill version.
Detected: suspicious.install_untrusted_source