Self Improving Agent

A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolv...

This skill is not obviously malicious, but it is inconsistent and potentially powerful: it claims to learn from every skill and to update other skills, yet the platform doesn't provide the global hooks it expects and it doesn't declare the credentials necessary to push changes. Before installing, ask the author how it will be triggered on your platform, what repository credentials (if any) it needs, and what explicit safeguards exist (e.g., ask-before-PR, sandboxed test runs, review-only mode). If you proceed, run it in an isolated workspace, do not grant global repo write tokens without manual review, and require that any PRs be human-reviewed before merging.

Type: OpenClaw Skill Name: selfgrowth-kay Version: 0.2.0 The skill bundle implements a 'self-improving' architecture that instructs the AI agent to autonomously modify its own skill files and instructions based on interaction history. While the provided bash scripts (hooks/pre-tool.sh, hooks/post-bash.sh) are limited to logging, the core logic in SKILL.md and README.md encourages the agent to use 'Write' and 'Edit' tools to rewrite its own codebase and memory. This self-modification capability creates a significant attack surface where the agent's primary instructions could be subverted through interaction, though no explicit evidence of intentional malice or data exfiltration was found in the current files.