ai-guardrails

ai-guardrails is a skill for Claude Code, Codex from VoDaiLocz/kilo-kit-mcp. It costs 58 tokens per session (1,068 once invoked), scanned A, original, Apache-2.0.

A security guide for autonomous AI agents that read untrusted content and use tools. It covers threats such as prompt injection, data theft, unsafe tool use, and endless action loops.

In plain words
What is it for?
Use it when designing safeguards for live agents, including checks around prompts, external data, tools, sandboxing, and repeated actions.
Why use it?
It helps reduce the risk that an agent follows malicious instructions, exposes sensitive data, or takes unsafe actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when designing safeguards for live agents, including checks around prompts, external data, tools, sandboxing, and repeated actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vodailocz/kilo-kit-mcp/ai-guardrails
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add VoDaiLocz/kilo-kit-mcp --skill ai-guardrails
Clone the repo
git clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/ai-guardrails/github.svg)](https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/ai-guardrails)
Your own site
<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/ai-guardrails"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/ai-guardrails/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-guardrails

Your own site · 80×15
<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/ai-guardrails"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/ai-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,068 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01068
Opus 5 $0.00029 $0.00534
Sonnet 5 $0.00012 $0.00214
Haiku 4.5 $0.00006 $0.00107

Measured 9d ago against content hash 36483a8c5b5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-guardrails scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/security/ai-guardrails/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Guardrails & Defense-in-Depth

Overview

The ai-guardrails skill provides a comprehensive framework for securing autonomous LLM agents. As agents interact with untrusted external data sources and perform actions on behalf of users, the attack surface expands significantly. This skill focuses on implementing multi-layered defenses to ensure agent safety, reliability, and integrity in live environments.

Threat Model

Autonomous agents face unique security challenges that require a proactive defense strategy:

  1. Direct Prompt Injection (DPI): Malicious input explicitly attempting to hijack the agent's core instructions.
  2. Indirect Prompt Injection (IPI): Injected instructions hidden in retrieved web pages, emails, or files that the agent processes.
  3. Prompt Leaking: Attempts to extract system instructions, internal reasoning paths, or proprietary data.
  4. Data Exfiltration: Unauthorized access and transfer of PII or sensitive internal data to external endpoints.
  5. SSRF (Server-Side Request Forgery) via Tool Use: Leveraging agent-enabled tools to probe internal networks or access forbidden resources.
  6. Agent Loop Exploitation: Crafting inputs that force the agent into infinite loops or resource-exhaustion scenarios.
  7. Tool Abuse: Circumventing intended tool usage patterns to execute malicious commands.

Core Defenses

Dual-LLM & Context Boundary Isolation

  • Pattern: Isolate instructions from data.
  • Implementation: Separate the Instruction Stream (system prompts, task logic) from the Content Stream (retrieved data).
  • Mechanism: Use a secondary, smaller "Sanitizer LLM" to filter untrusted content before it reaches the main reasoning engine.

Indirect Prompt Injection (IPI) Defenses

  • Detection: Utilize structured markup (e.g., XML tags like <untrusted_content>) to wrap retrieved data.
  • Neutralization: Instruct the agent to strictly ignore any instructions contained within tagged content blocks.

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 69 lines · 58 tokens per session scan A 36483a8c5b5e

Subscribe to this mod's changes

ai-guardrails is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,068 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

llm-structured-output

Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.

hybridlabor-api/bdb-dev-optimized-agent-skills · 42 tokens

drizzle-orm-expert

Expert in Drizzle ORM for TypeScript — schema design, relational queries, migrations, and serverless database integration. Use when building type-safe database layers with Drizzle.

hybridlabor-api/bdb-dev-optimized-agent-skills · 41 tokens

landing-page-generator

Generates high-converting Next.js/React landing pages with Tailwind CSS. Uses PAS, AIDA, and BAB frameworks for optimized copy/components (Heroes, Features, Pricing). Focuses on Core Web Vitals/SEO.

hybridlabor-api/bdb-dev-optimized-agent-skills · 50 tokens

tdmcp-pipeline

Orchestrates the tdmcp feature team end-to-end: design/wireframe → build → integrate → QA → release. Use whenever the user wants to build, implement, develop, ship, or add one or more tdmcp features/tools/effects/controls/AI-prompts for TouchDesigner, or to run them through a coordinated design→develop→QA→deploy…

hybridlabor-api/bdb-dev-optimized-agent-skills · 128 tokens

startcycle-graph-user

Use when a task needs a small, throwaway multi-agent fan-out (a couple of parallel workers plus a review pass) in ANY project, without the full /startcycle-graph contract — no .agents/graph.md bootstrap, no state.json schema, no persistent files. Model-tiered by role (opus plan, sonnet review, haiku or an external CLI…

hybridlabor-api/bdb-dev-optimized-agent-skills · 102 tokens

memb-skill

BDB local-first long-term memory engine (memB). Use when querying, remembering, or adapting preferences, code architectures, and developer patterns across tasks.

hybridlabor-api/bdb-dev-optimized-agent-skills · 36 tokens