Clawdbot Security Check

Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when user asks to "run security check", "audit clawdbot", "check security hardening", or "what vulnerabilities does my Clawdbot have". This skill uses Clawdbot's internal capabilities and file system access to inspect configuration, detect misconfigurations, and recommend remediations. It is designed to be extensible - new checks can be added by updating this skill's knowledge.

Install only if you are comfortable with the skill inspecting local Clawdbot configuration and possibly displaying sensitive configuration values. Treat normal audit use as read-only, but do not run --fix unless you intentionally want persistent changes to bot policies, logging behavior, and file permissions after reviewing and backing up affected files.

Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill The skill's primary purpose is a legitimate 'read-only security audit'. However, there is a critical contradiction: the `skill.json` explicitly declares `"readOnly": true` and `"modifiesSettings": false`, while both `SKILL.md` and `README.md` describe a `--fix` flag that 'applies guardrail remediations' by modifying configuration files and permissions. This inconsistency is a significant vulnerability in the skill's self-description and could lead to unexpected agent behavior or a misrepresentation of its true capabilities, making it suspicious despite the otherwise benign intent of a security audit.