Claude Memory

• Risk level: Low
• Analyzed: Apr 5, 2026, 3:36 PM
• Findings: 0
• Version: 1.2.0

Overview

The skill is internally consistent: it provides a local, file-based memory system and only requires creating/reading files in the agent workspace — no external credentials, installs, or unexpected network behavior are present.

This skill creates and manages persistent local files containing personal preferences, confirmations, and project data — review and secure the workspace you pass to the init script (permissions, backups, encryption). Confirm your deployment enforces the SKILL.md's 'ONLY load in main session / DO NOT load in shared contexts' rule, otherwise private MEMORY.md content could be exposed. Review scripts/init_memory.py (it's small and benign) and the provided references to ensure the write rules meet your privacy policy. Finally, note the skill has unknown provenance (no homepage, owner ID only); if provenance matters to you, ask the publisher for more information before installing.