Security checks across malware telemetry and agentic risk
The skill has a plausible child-behavior video analysis purpose, but it asks for and handles sensitive videos, identifiers, credentials, cloud records, and local tokens in ways that are broader and less clearly controlled than users would expect.
Review carefully before installing. Only use this with explicit guardian consent, non-sensitive test media first, and a dedicated open-id that is not an API key, phone number, or reusable credential. Avoid installing until the publisher removes api-key-as-open-id handling, documents the exact cloud endpoints/data retention, secures token storage, narrows triggers, removes unrelated camera CRUD/payment flows, and fixes the invalid dependency.
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:VirusTotal findings are pending for this skill version.