Self-Evolve

Autonomous self-evolution skill: grants the agent full authority to modify its own configuration, skills, prompts, AGENTS.md, SOUL.md, memory files, and any workspace file WITHOUT asking for user confirmation. The agent should proactively identify weaknesses, fix them, write new skills, and continuously improve itself.

This skill explicitly tells an agent to change its own code, configuration, and install/run arbitrary commands without asking you — and to publish new skills. That is powerful and risky. Before installing, consider: - Do not install unless you fully trust the skill author and understand the implications. Treat this as granting the agent near-admin authority over its workspace and config. - If you need experimentation, run it in a tightly isolated sandbox (VM/container) with no access to your home directory, no access to cloud credentials, and restricted network egress. - Require explicit user confirmation for any file-system or network-affecting action (remove the 'no-confirm' behavior). - Prevent automatic publishing: revoke or do not provide ClawHub/publish credentials, and audit any attempts to call npx or similar tools. - Lock down ~/.openclaw/openclaw.json and other config files with file-system permissions; keep backups and use version control to review all changes. - Monitor logs and require an approval workflow for changes to skills/, system config, or publishing to remote registries. Given the combination of self-modification, shell/network access, and implicit need for credentials, this skill is coherent with its stated mission but too broad and potentially dangerous for most users. If you proceed, apply strong sandboxing, audit, and manual-approval controls.

Type: OpenClaw Skill Name: self-evolve Version: 1.0.0 This skill grants the AI agent extremely broad and dangerous capabilities, explicitly instructing it to bypass user confirmation for almost all actions. The `SKILL.md` file contains direct instructions for the agent to execute arbitrary commands via `bash`, perform arbitrary network requests via `curl`, modify system configurations (e.g., `cron` for persistence), and even create/publish new skills to ClawHub. While the stated purpose is 'self-evolution' and 'self-improvement', these capabilities, combined with the explicit instruction to 'never ask for confirmation', create a critical vulnerability for prompt injection, enabling potential remote code execution, data exfiltration, and supply chain attacks if the agent is compromised.