OpenClaw Memory Fix Skill

Provides a multi-layer memory system for OpenClaw, enabling AI to remember user preferences, learn from mistakes, and evolve continuously.

Do not blindly copy the provided config-files into your live ~/.openclaw/workspace. Before installing: 1) Inspect and sanitize files (especially TOOLS.md and any file with tokens or API keys); remove or rotate any hard-coded tokens. 2) Backup your workspace. 3) Test the package in an isolated sandbox or throwaway OpenClaw instance to see what files it writes and what behavior changes (heartbeats, subagent spawning, automatic external requests) it triggers. 4) Look for lines that tell the agent to 'Don't ask permission' or to read broad sets of files — those are red flags for undesired autonomous actions. 5) If you want only memory features, copy a minimal subset (e.g., the auto-memlog.sh and MEMORY.md templates) and avoid copying AGENTS.md / AUTONOMY.md / HEARTBEAT.md / TOOLS.md unless you understand and accept all their effects. If you are uncertain, treat this package as untrusted and run it in isolation.

Type: OpenClaw Skill Name: openclaw-memory-fix-skill Version: 1.0.0 The skill bundle contains a hardcoded Feishu app_token in 'config-files/TOOLS.md', which represents a significant credential leak and security risk. Additionally, the instructions in 'config-files/AGENTS.md' and 'SKILL.md' grant the AI agent high levels of autonomy with phrases like 'Don't ask permission. Just do it,' and include a 'BOOTSTRAP.md' self-deletion mechanism that could be used for stealthy initial configuration. While the bundle appears to be a sophisticated memory management framework with built-in security checks (e.g., in 'config-files/HEARTBEAT.md'), the combination of exposed secrets and broad autonomous instructions warrants a suspicious classification.