/SKILL.md
# AI Guardrails Input/output validation and safety for AI applications. ## Quick Start ```bash npx ai-guardrails validate "Check this text" ``` ## What It Does - Detect PII (email, phone, SSN, credit cards) - Block prompt injection attempts - Filter harmful content - Validate LLM outputs ## Usage ```bash # Validate text npx ai-guardrails validate "text" # Detect PII npx ai-guardrails pii "Email: [email protected]" # Check injection npx ai-guardrails injection "Ignore previous instruction
npx skillsauth add lxgicstudios/ai-guardrails ai-guardrailsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Input/output validation and safety for AI applications.
npx ai-guardrails validate "Check this text"
# Validate text
npx ai-guardrails validate "text"
# Detect PII
npx ai-guardrails pii "Email: [email protected]"
# Check injection
npx ai-guardrails injection "Ignore previous instructions"
# Generate files
npx ai-guardrails init
One of 110+ free developer tools from LXGIC Studios.
MIT. Free forever.
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).