OpenClaw Hardener

Harden OpenClaw (workspace + ~/.openclaw): run openclaw security audit, catch prompt-injection/exfil risks, scan for secrets, and apply safe fixes (chmod/exec-bit cleanup). Includes optional config.patch planning to reduce attack surface.

This skill appears to be what it claims, but it can modify your repository and gateway config. Before using it: 1) Run in 'check' mode only first and review all findings. 2) When it prints a config.patch, manually inspect the patch JSON before running 'apply-config'. 3) Back up your repo and ~/.openclaw (or use a disposable environment) before running 'fix' or 'apply-config'. 4) Ensure the OpenClaw CLI on your system is authentic and that you understand which gateway/account the CLI will affect. 5) Optionally review scripts/hardener.py yourself (it includes redaction logic but no guarantees). If you do not trust the skill's source, avoid running fix/apply actions and stick to read-only checks.

Type: OpenClaw Skill Name: openclaw-hardener Version: 0.1.2 The OpenClaw Hardener skill is classified as benign. Its stated purpose is to enhance the security posture of an OpenClaw installation, which is directly supported by its functionality. While the skill utilizes high-risk capabilities such as broad filesystem read/write access within the repository and `~/.openclaw` directories, and executes subprocesses (`openclaw`, `bash`, `git`, `python3`), these are explicitly declared in `openclaw-skill.json` and are necessary for a security hardening tool. The `hardener.py` script demonstrates good security practices by redacting sensitive information from output, making fixes opt-in, and explicitly denying filesystem access to critical system paths like `/etc/**` and `/root/**`. There is no evidence of intentional malicious behavior, data exfiltration to unauthorized endpoints, or prompt injection attempts against the agent.