Self_Improving_ClawAgent

Generates and debugs code, scaffolds projects, navigates antigravity environments, and performs resilient YouTube research with fallback data modeling.

This skill is internally coherent with its 'self-improving' purpose but carries real risk because it is allowed to modify its own instruction files and execute local code. Before installing, consider: 1) Run the skill in a tightly sandboxed environment (ephemeral VM/container) isolated from sensitive files and credentials. 2) Remove or narrow the manifest read permission (do not allow './*'); restrict writes to only the exact files you consent to (SKILL.md/MEMORY.md/SOUL.md) if you accept them. 3) Require manual approval for any self-patch or automatic SKILL.md overwrite (disable autonomous self-patching or set an explicit confirmation step). 4) Review and harden refine.py (the BASE_DIR check helps, but ensure BASE_DIR is correctly set and that no symlink/traversal bypass exists). 5) Keep the repository under version control and monitor backups (.bak) and commit diffs after each change. 6) Prefer disabling autonomous invocation (disable-model-invocation) while you audit runtime behavior. 7) If you must use it, limit network access and monitor outbound connections — the current code has no network exfiltration, but self-modification could add it later. If you are uncomfortable with a tool that can rewrite its own instructions, do not install or only run it in a disposable test environment.

Type: OpenClaw Skill Name: self-improving-clawagent Version: 1.0.1 The bundle implements a 'self-evolving' architecture that allows the AI agent to rewrite its own logic and files (SKILL.md, MEMORY.md) via refine.py. While refine.py includes a path-traversal check to restrict operations to the local directory, the explicit instructions in MASTER_PROMPT.md for the agent to perform a 'Self-Rewrite' and 'Logic Optimization' create a high-risk environment for persistent prompt injection. The request for 'local_code_execution' in manifest.json combined with self-modifying capabilities is a significant security risk, though no evidence of intentional malice or data exfiltration was found.