Self-Improving Agent (tuituitu)

Self-improvement and learning skill for the agent. Activate when: - User gives feedback on agent's performance - Agent makes mistakes or errors - User asks a...

This skill will persistently modify the agent's memory and persona files, which can permanently change agent behavior. Before installing, decide whether you want the agent to auto-edit those files without approval. Recommended precautions: 1) Require user confirmation before any file changes; 2) Restrict writable paths (only a single approved memory file) and backup originals; 3) Disable autonomous invocation or set the skill to require explicit user invocation; 4) Review diffs of MEMORY.md/AGENTS.md/SOUL.md changes before applying or committing; 5) Ensure sensitive files are excluded from the agent workspace and that file permissions are locked down; 6) Ask the publisher for clarification: exactly which files will be modified, whether the skill will run commands/cron jobs, and whether writes can be scoped or reviewed. If you cannot get those assurances, treat the skill as higher-risk and avoid enabling persistent/autonomous behavior.

Type: OpenClaw Skill Name: self-improving-agent-tuituitu Version: 1.0.0 The skill bundle provides instructions for the agent to autonomously modify its own memory and configuration files (e.g., MEMORY.md, SOUL.md, AGENTS.md) based on user feedback and self-reflection. While this is aligned with the stated goal of 'self-improvement,' the lack of validation or sanitization mechanisms creates a significant vulnerability to persistent indirect prompt injection. A user could potentially trick the agent into 'learning' and hardcoding malicious behaviors or exfiltration instructions into its core persona files, which would persist across future sessions.