self-guardianLightweight self-monitoring and self-constraining rules to prevent accidental file deletions, dangerous commands, and risky operations. Activates automatical...
Install via ClawdBot CLI:
clawdbot install vaderyang/self-guardianGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 21, 2026
A developer requests to delete temporary build artifacts or old log files. The skill triggers on keywords like 'clean up' and 'delete file', prompting the agent to verify the file paths aren't critical (e.g., .env or database files) and suggest safer alternatives like moving to trash or using dry runs before permanent deletion.
During a database schema update, a user asks to drop old tables. The skill detects patterns like 'drop table' and blocks execution, enforcing a pre-action checklist to confirm reversibility and authorization, and suggesting backups or transactional updates instead to prevent data loss.
A DevOps engineer modifies CI/CD files like .github/workflows or Dockerfile. The skill activates on keywords like 'modify file' and tags these as 'confirm first' files, requiring the agent to pause and explain the impact of changes to avoid breaking deployment pipelines.
An admin runs shell commands with sudo or chmod for server maintenance. The skill blocks risky patterns like 'sudo' and 'chmod 777', prompting confirmation and recommending minimal privileges or safer alternatives to prevent security breaches or system instability.
A content manager performs bulk updates to website files. The skill throttles operations over 3 files, listing all affected files first and checking for sensitive data like credentials or keys to ensure only intended, safe files are modified.
Offer this skill as part of a subscription-based AI agent platform, charging monthly fees for enhanced safety features. Revenue comes from tiered plans based on usage limits, priority support, and custom rule configurations for enterprises.
Provide consulting services to integrate the skill into existing AI systems, with revenue from one-time setup fees and ongoing maintenance contracts. This targets organizations needing tailored safety rules for specific workflows or compliance requirements.
Release the skill as open-source to build community adoption, then monetize through premium add-ons like advanced analytics, enterprise-grade support, or proprietary extensions for high-risk industries like finance or healthcare.
💬 Integration Tip
Integrate this skill by adding its activation keywords and patterns to your AI agent's monitoring layer, ensuring it runs pre-action checks automatically before any file or shell operation to enforce safety without user intervention.
Scored Jun 19, 2026
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
GEO Audit — AI Search Visibility Checker for ChatGPT, Perplexity, Claude & Gemini. 29-point GEO readiness checklist: robots.txt AI crawler access, Index...
Audit and analyze Solidity smart contracts for security vulnerabilities. Use when reviewing, auditing, or analyzing smart contracts, Solidity code, DeFi prot...