Security checks across malware telemetry and agentic risk
This skill is not clearly malicious, but it deserves Review because it processes highly sensitive pregnancy-related audio/video, uses cloud history and identity flows, and has under-scoped automatic actions.
Install only if you are comfortable with cloud processing of pregnancy-related home or clinic audio/video, persistent user identifiers, local token storage, paid-service flows, and automatic report/history access. The monitored person and any bystanders should explicitly consent, and spouse or emergency-contact alerts should be configured as opt-in. The publisher should replace the nonexistent `yaml` dependency, document the actual analysis API, restrict video URLs to authorized sources, and make identity/report access and token persistence explicit before this is treated as routine.
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:66/66 vendors flagged this skill as clean.