Auto-improving AI agent that learns from every execution, extracts patterns, and continuously optimizes itself. 17-minute autonomous loop with confidence sco...

This package is a stubbed self-improvement agent: the shipped code only runs an infinite 17‑minute sleep/loop and contains many TODOs, but the documentation promises broad behaviors (reading execution history, extracting patterns, auto‑publishing skills). Before installing or running: - Treat it as untrusted code: inspect and approve any code changes before running. - Run in a sandbox or isolated environment (container, VM) and avoid giving it access to sensitive logs, home directory, cloud credentials, or keys. - Note the SKILL.md lists Bash/Exec/Read/Write tools — those would let the agent run arbitrary shell commands and read files if implemented; only allow them if you trust the author. - If you want the feature set (data capture, auto‑publish), require explicit documentation of what data is read, where data is stored/transmitted, and what credentials are needed. Demand least-privilege design and auditability before granting those privileges. - Because the implementation is incomplete, consider waiting for a mature release or ask the author for a security design and provenance of published skills before use.

Type: OpenClaw Skill Name: auto-improver Version: 1.0.0 The skill bundle makes grandiose claims about being a 'self-evolving AI engine' with autonomous loops and commercial pricing tiers, but the actual implementation in `src/index.js` is a skeleton script that does nothing but log messages and sleep. The discrepancy between the marketing-heavy `SKILL.md` and the non-functional code is highly suspicious. Furthermore, it requests high-privilege tools (`Bash`, `Exec`) and uses 'meta-skill' framing that could be used to trick an AI agent into performing unauthorized system modifications under the guise of 'self-improvement'.