Self Improving Agent Local

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...

This skill appears coherent and low-risk for its stated local self-improvement purpose, but take these precautions before installing or enabling hooks: - Review the scripts (activator.sh, error-detector.sh, extract-skill.sh and the hook handlers) yourself. They run with your user permissions and can write files in the workspace. - Be careful what you log: the error template suggests appending full source and file contents to .learnings/ERRORS.md. Do NOT include secrets, private keys, or credentials in learning entries or when promoting entries to shared workspace files. - Prefer project-scoped activation (project-level settings) rather than user/global hooks until you verify behavior. Use matcher filters to limit when hooks run. - If you pull the repository, verify the GitHub source and its commit history if you need higher assurance. - Test in an isolated workspace first: create a temporary project, enable the minimal activator-only setup, and observe outputs before enabling PostToolUse hooks or running extract-skill.sh. If you want, I can extract the exact lines in the scripts that create or write files and highlight anything that writes outside the current workspace or that could send data externally.

Type: OpenClaw Skill Name: self-improving-agent-local Version: 1.0.10 The skill instructs the AI agent to modify its own operational context files (e.g., `SOUL.md`, `AGENTS.md`, `TOOLS.md`, `CLAUDE.md`, `.github/copilot-instructions.md`) based on 'learnings' and 'recurring patterns' as detailed in `SKILL.md`. This self-modification capability, while intended for benign self-improvement, creates a significant prompt injection attack surface. If an attacker can influence the agent's 'learnings' (e.g., through crafted error messages or user prompts), they could potentially inject malicious instructions into these persistent context files, altering the agent's future behavior. Additionally, the `scripts/extract-skill.sh` allows the agent to create new skills, which could also be abused if the extracted 'learning' is malicious. There is no clear evidence of intentional harmful behavior like data exfiltration or backdoors in the provided code.