Assistant
Security checks across malware telemetry and agentic risk
Overview
This is a plain instruction-only personal assistant skill with no code, install steps, credentials, or hidden capabilities; users should only be aware that it encourages remembering preferences and prior context.
This skill appears safe and coherent as an instruction-only personal assistant. Before installing, consider whether you want the assistant to remember preferences or prior context, and periodically review any saved memory if your agent platform supports it.
VirusTotal
65/65 vendors flagged this skill as clean.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If the agent has memory enabled, it may preserve preferences or prior-context notes that affect future assistance.
These instructions encourage retaining and reusing user preferences and prior conversation context. That is coherent for a personal assistant, but users should know that saved context can include sensitive personal details or influence future behavior.
Keep notes on preferences and patterns — learn how the person works ... Remember context from previous conversations — continuity matters
Use the skill with normal memory hygiene: review saved notes when possible, avoid storing unnecessary sensitive details, and correct or delete inaccurate preferences.