skills.rest
tylerjrbuell
tylerjrbuellCOMMUNITY
Explore all skills by this author →
GitHub

identity-and-guardrails

Detect prompt injection, mask PII, and enforce behavioral contracts for TypeScript agents.

21|4|Updated Feb 19, 2026
Search Tags:#audit#guardrails#pii#kill-switch#prompt-injection#behavioral-contracts
One-click install
npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill identity-and-guardrails
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: identity-and-guardrails
Source: https://github.com/tylerjrbuell/reactive-agents-ts/tree/main/apps/docs/skills/identity-and-guardrails
Command: npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill identity-and-guardrails

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents unsafe or uncontrolled agent behavior by detecting prompt injection, masking PII, enforcing behavioral contracts, and providing runtime kill-switch and identity controls so agents can run safely in production environments.

Core Features & Use Cases

  • Prompt injection detection: Identify and block instructions intended to override system or developer-imposed rules.
  • PII masking and toxicity checks: Detect and mask sensitive personal data and toxic content before processing or returning results.
  • Behavioral contracts and tool restrictions: Define denied/allowed tools, max iterations, max tool calls, and output length limits for strict runtime enforcement.
  • Kill-switch and auditability: Support pause/resume/stop/terminate controls and record tool calls and guardrail decisions for compliance and debugging.
  • Use Case: Deploy a public-facing customer support agent that must never call destructive tools, must redact customer data, require disclosure of AI identity, and provide an audit trail for each session.

Quick Start

Use the identity-and-guardrails skill to build an agent that enforces prompt injection detection, PII masking, behavioral contracts, runtime pause/resume/stop controls, and audit logging.

Frequently Asked Questions about identity-and-guardrails

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect and block prompt injection attacks in AI agents?▼

Prompt injection detection identifies and blocks malicious instructions attempting to override system rules in AI agents. This skill provides behavioral contracts and guardrails to prevent uncontrolled agent behavior in public-facing, multi-tenant environments.

How do I mask PII and enforce tool restrictions for customer support agents?▼

PII masking detects and redacts sensitive personal data before processing results, while behavioral contracts define allowed tools and output limits. This enforces strict runtime safety for agents handling customer data.

Can I use runtime kill-switch controls to pause or terminate AI agent sessions?▼

Yes, runtime kill-switch controls support pause, resume, stop, and terminate actions for AI agents. This allows you to halt unsafe agent behavior immediately and record tool calls for compliance auditing.

Does this work with TypeScript projects deployed in multi-tenant environments?▼

Yes, this applies to Reactive Agents TypeScript projects deployed in multi-tenant or public-facing contexts. It provides session identity tracking, tool restrictions, and human approval gates for production environments.

What is the best way to enforce behavioral contracts and audit logging for AI agents?▼

Behavioral contracts enforce max iterations, tool call limits, and output length restrictions, while audit logging records guardrail decisions and tool calls. This satisfies runtime safety and policy enforcement requirements for compliance.

Why do I need identity controls for public-facing AI agents?▼

Identity controls require disclosure of AI identity and track session activity to prevent unsafe behavior in production. They ensure agents operate within defined behavioral boundaries and provide auditability for each session.

Related Skills

Explore More Software Engineering Skills→
cdrgurucdrguru
1

gemini-cli-init

Initialize Gemini CLI configuration and auditor persona for the PACK workflow.

Community
Intermediate
chicongstchicongst
2

sre-engineering

Coordinate production incident response and post-mortem analysis.

Community
Advanced
joonlabjoonlab
8

deep-agents-orchestration

Orchestrates multi-agent workflows in LangGraph with task delegation and human approval.

Community
Advanced
pluginagentmarketplacepluginagentmarketplace
3

input-output-guardrails

Enforce input and output guardrails on AI interactions.

Community
Basic