Security checks across malware telemetry and agentic risk
This skill is not clearly malicious, but it needs review because it can send unprompted messages and store user interaction history without enough consent, retention, or frequency controls.
Install only if you intentionally want an agent to send proactive check-ins, change alert timing based on engagement, and keep local interaction history. Before use, require explicit user opt-in, add clear disable and delete controls, enforce cadence logging for micro-initiations, use separate state directories per user or agent, set retention limits, and avoid sending stored context summaries to external model APIs without review. Static scan was clean and VirusTotal was pending; this Review verdict is based on the artifact behavior itself, not malware telemetry.
}
def _save_context(self) -> None:
"""Save context to disk with backup rotation."""
_safe_save_state(self.context_file, self.context)
def get_all_messages(self) -> List[Dict[str, Any]]:66/66 vendors flagged this skill as clean.