Skill Overview
---
name: clawdbot-self-security-audit
description: 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.
homepage: https://github.com/TheSethRose/Clawdbot-Security-Check
metadata: {"clawdbot":{"emoji":"🔒","os":["darwin","linux"],"requires":{"files":["read"],"tools":["exec","bash"]},"install":[{"id":"read-skill","kind":"skill","name":"clawdbot-self-security-audit","label":"Install security audit skill","bins":["SKILL.md"]}]}}
---
# Clawdbot Self-Security Audit Framework
This skill empowers Clawdbot to audit its own security posture using first-principles reasoning. Rather than relying on a static script, Clawdbot learns the framework and applies it dynamically to detect vulnerabilities, understand their impact, and recommend specific remediations.
## Core Philosophy
> "Security through transparency and self-awareness." — Inspired by ᴅᴀɴɪᴇʟ ᴍɪᴇssʟᴇʀ
Clawdbot should know its own attack surface. This skill embeds that knowledge directly.
## Security Principles
Running an AI agent with shell access requires caution. Focus on three areas:
1. **Who can talk to the bot** — DM policies, group allowlists, channel restrictions
2. **Where the bot is allowed to act** — Network exposure, gateway binding, proxy configs
3. **What the bot can touch** — Tool access, file permissions, credential storage
Start with the smallest access possible and widen it as you gain confidence.
## Trust Hierarchy
Apply appropriate trust levels based on role:
| Level | EntityBot Reviews(1)
A framework, not a scanner, and better for it
Rather than shipping a fixed checklist, this skill installs a reasoning framework the agent applies to its own configuration, organised around three questions: who can talk to the bot, where it may act, and what it can touch. That framing is more durable than a static script because it survives config schema changes. The trade-off is that output quality depends entirely on the reasoning step, so results are less reproducible than a scanner's, and there is no numeric score to regress against. It is read-only by design, which makes it safe to run unattended, but it also means it will never fix what it finds.
Use case: Periodic self-audit of an agent's own exposure: DM policy, gateway binding, tool and credential access.
Study Guides(1)
Auditing an agent's own attack surface in three questions
# Self-security audit This is a reasoning framework rather than a scanner, which makes it portable across config schema changes but dependent on how carefully it is applied. ## Three questions 1. Who can talk to the bot: DM policy, group allowlists, channel restrictions. 2. Where the bot is allowed to act: network exposure, gateway binding, proxy configuration. 3. What the bot can touch: tool access, file permissions, credential storage. Start from the smallest access that works and widen only with a reason. A trust hierarchy by role keeps that honest: the more privileged the requester or tool, the narrower the default should be. ## Run it read-only The framework is designed to inspect configuration with read access and shell tooling, then recommend remediations. Because it makes no changes, it is safe to schedule. Expect findings to be configuration-level rather than exploit-level, and expect reproducibility to be lower than a fixed script: two runs can surface different framing of the same posture.
Quick Facts
Install
npx clawhub@latest install clawdbot-security-check