How do I install the Hivefence skill?

Run npx skillmds@latest add seojoonkim/hivefence in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hivefence safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hivefence?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hivefence free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hivefence?

seojoonkim (@seojoonkim) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hivefence by seojoonkim — Agent Skill

Name: Hivefence
Rating: 4.666666666666667 (3 reviews)
Author: seojoonkim

Hivefence

Runtime security layer for autonomous AI agents. Covers 6 attack surfaces: prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, and cascade amplification. Collective immunity network — when one agent detects an attack, all connected agents become immune. 600+ patterns, token splitting bypass defense with 6-pass normalization.

seojoonkim Updated Sep 10, 2026

File contents

HiveFence v1.2.0

🐝 The Runtime Security Layer for Autonomous AI Agents

When one is attacked, all become immune. Defense-in-depth for agentic systems.

What is HiveFence?

HiveFence is a comprehensive runtime security framework that protects AI agents across the full attack surface — not just prompt injection:

Detect — Scan incoming prompts against 600+ patterns across 6 attack categories
Report — New attack patterns are hashed and submitted to the network
Immunize — Community validates the pattern, then every connected agent gets the update

Attack Surface Coverage

Category	Severity	Patterns
Prompt Injection	CRITICAL-HIGH	Instruction override, jailbreak, impersonation, extraction
Supply Chain Injection	CRITICAL	Malicious skills, lifecycle hooks, credential exfil
Memory Poisoning	HIGH	Persistent write injection to agent config files
Action Gate Bypass	HIGH	Unauthorized financial, credential, access, destructive actions
Unicode Steganography	HIGH	Bidi overrides, zero-width chars, invisible instructions
Cascade Amplification	MEDIUM	Infinite agent spawning, recursive loops, cost explosion

Features

🔍 Real-time Detection — Pattern matching + semantic analysis in <50ms
🌍 Multi-language — EN, KO, JA, ZH attack detection
🗳️ Community Governance — Democratic voting on new patterns
🔐 Privacy-preserving — Only SHA-256 hashes shared, not raw content
📊 Severity Scoring — Risk-based prioritization (0-100)
⚡ Edge-first — Cloudflare Workers at 300+ locations

Installation

# Via ClawdHub
npx clawhub install hivefence

# Or via npm
npm install hivefence

Quick Start

import { protect, reportThreat } from 'hivefence'

// Scan incoming prompt
const result = await protect(userInput)

if (result.blocked) {
  console.log(`Threat blocked: ${result.category}`)
  // Pattern automatically reported to network
}

API Endpoints

Method	Endpoint	Description
POST	`/api/v1/threats/report`	Submit new threat pattern
GET	`/api/v1/threats/pending`	Get patterns awaiting votes
POST	`/api/v1/threats/:id/vote`	Vote on a pattern
GET	`/api/v1/threats/latest`	Fetch approved patterns
GET	`/api/v1/stats`	Network statistics

Base URL: https://hivefence-api.seojoon-kim.workers.dev

Security Stack Recommendation

For maximum protection, use HiveFence with:

ACIP — Advanced Cognitive Inoculation Prompt (behavioral boundaries)
HiveFence — Runtime security + collective immunity
SkillGuard — Audit skills before installation

License

---name: hivefencedescription: Runtime security layer for autonomous AI agents. Covers 6 attack surfaces: prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, and cascade amplification. Collective immunity network — when one agent detects an attack, all connected agents become immune. 600+ patterns, token splitting bypass defense with 6-pass normalization.---# HiveFence v1.2.0🐝 **The Runtime Security Layer for Autonomous AI Agents**> When one is attacked, all become immune. Defense-in-depth for agentic systems.## What is HiveFence?HiveFence is a comprehensive runtime security framework that protects AI agents across the full attack surface — not just prompt injection:1. **Detect** — Scan incoming prompts against 600+ patterns across 6 attack categories2. **Report** — New attack patterns are hashed and submitted to the network3. **Immunize** — Community validates the pattern, then every connected agent gets the update## Attack Surface Coverage| Category | Severity | Patterns ||----------|----------|----------|| Prompt Injection | CRITICAL-HIGH | Instruction override, jailbreak, impersonation, extraction || Supply Chain Injection | CRITICAL | Malicious skills, lifecycle hooks, credential exfil || Memory Poisoning | HIGH | Persistent write injection to agent config files || Action Gate Bypass | HIGH | Unauthorized financial, credential, access, destructive actions || Unicode Steganography | HIGH | Bidi overrides, zero-width chars, invisible instructions || Cascade Amplification | MEDIUM | Infinite agent spawning, recursive loops, cost explosion |## Features- 🔍 **Real-time Detection** — Pattern matching + semantic analysis in <50ms- 🌍 **Multi-language** — EN, KO, JA, ZH attack detection- 🗳️ **Community Governance** — Democratic voting on new patterns- 🔐 **Privacy-preserving** — Only SHA-256 hashes shared, not raw content- 📊 **Severity Scoring** — Risk-based prioritization (0-100)- ⚡ **Edge-first** — Cloudflare Workers at 300+ locations## Installation```bash# Via ClawdHubnpx clawhub install hivefence# Or via npmnpm install hivefence```## Quick Start```javascriptimport { protect, reportThreat } from 'hivefence'// Scan incoming promptconst result = await protect(userInput)if (result.blocked) { console.log(`Threat blocked: ${result.category}`) // Pattern automatically reported to network}```## API Endpoints| Method | Endpoint | Description ||--------|----------|-------------|| POST | `/api/v1/threats/report` | Submit new threat pattern || GET | `/api/v1/threats/pending` | Get patterns awaiting votes || POST | `/api/v1/threats/:id/vote` | Vote on a pattern || GET | `/api/v1/threats/latest` | Fetch approved patterns || GET | `/api/v1/stats` | Network statistics |**Base URL:** https://hivefence-api.seojoon-kim.workers.dev## Security Stack RecommendationFor maximum protection, use HiveFence with:1. **ACIP** — Advanced Cognitive Inoculation Prompt (behavioral boundaries)2. **HiveFence** — Runtime security + collective immunity3. **SkillGuard** — Audit skills before installation## Links- **Website:** https://hivefence.com- **GitHub:** https://github.com/seojoonkim/hivefence- **API Docs:** https://hivefence.com/docs## LicenseMIT © 2026 Simon Kim (@seojoonkim)

Frequently asked questions