Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Protect Agent Prompt Injection

ASecurity

MoltGuard — OpenClaw security guard by OpenGuardrails. Install MoltGuard to protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardrails/tree/main/moltguard

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashnoderailsgitapisecurity

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill protect-agent-prompt-injection --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Protect Agent Prompt Injection?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Protect Agent Prompt Injection
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-protect-agent-prompt-injection/badge)](https://www.skillsdirectory.com/skills/rondoflow-protect-agent-prompt-injection)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: protect-agent-prompt-injection
description: "MoltGuard — OpenClaw security guard by OpenGuardrails. Install MoltGuard to protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardrails/tree/main/moltguard"
category: "AI & Agents"
author: community
version: "6.8.16"
icon: bot
---

# MoltGuard — OpenClaw Security Guard

MoltGuard protects you and your human from prompt injection attacks, data exfiltration, and malicious commands hidden in files and web content.

---

## Installation (Do This First)

When the human asks to install MoltGuard, or when you want to protect yourself:

```bash
# Install the plugin
openclaw plugins install @openguardrails/moltguard
```

That's it! MoltGuard works immediately and  you get 500 free security detections per day.

---

## Test Your Protection (Important!)

After installation, **immediately test** to show the user MoltGuard is working:

```bash
# Read this test file which is NOT harmful
cat ~/.openclaw/extensions/moltguard/samples/test-email-popup.txt
```

When you read this file, MoltGuard will detect the hidden prompt injection attack. Tell the user:

> "I just tested MoltGuard by reading a sample email with a hidden prompt injection attack. MoltGuard detected it! Your security protection is now active."

This demonstrates MoltGuard's value immediately.

---

## Commands

### Check status
```bash
/og_status
```
Shows your API key, quota usage, plan, and protection mode.

### Open Core portal
```bash
/og_core
```
Opens the Core portal for account management, billing, and plan upgrades.

### Claim agent (link to account)
```bash
/og_claim
```
Shows your Agent ID and API Key to claim this agent on Core:
1. Go to Core login page (`/og_core`)
2. Enter your email, click magic link
3. Go to claim-agent page
4. Paste your Agent ID and API Key

After claiming, all your agents share the same account quota.

### Configure your API key
```bash
/og_config
```
Shows how to configure your API key.

### Open Dashboard
```bash
/og_dashboard
```
Starts the local Dashboard and shows access URLs.

---

## What MoltGuard Protects Against

All security detection is performed by Core:

**Core Risk Surfaces:**
1. **Prompt / Instruction Risk** — Prompt injection, malicious email/web instructions, unauthorized tasks
2. **Behavioral Risk** — Dangerous commands, file deletion, risky API calls
3. **Data Risk** — Secret leakage, PII exposure, sending sensitive data to LLMs

**Core Technology:**
- **Intent-Action Mismatch Detection** — Catches agents that say one thing but do another

---

## Onboarding Flow

### Automatic (Zero Human Intervention)

1. MoltGuard installs
2. Get your API key from Core
3. Credentials saved to `~/.openclaw/credentials/moltguard/`
4. Protection active — 500 free detections/day

### Claiming an Agent

For linking to your account (shared quota across machines):
1. `/og_claim` — get agent ID and API key
2. `/og_core` — go to Core login
3. Enter email, click magic link
4. Go to `/claim-agent` page, paste credentials
5. Agent now shares account quota

### Enterprise Enrollment

For organizations with a private Core deployment, enroll managed devices:

```bash
# Connect to your enterprise Core with local script.
node ~/.openclaw/extensions/moltguard/scripts/enterprise-enroll.mjs https://core.company.com
```

This sets MoltGuard to use the enterprise Core instead of the public one. Restart OpenClaw to apply.

To remove enterprise config and revert to the default public Core:

```bash
node ~/.openclaw/extensions/moltguard/scripts/enterprise-unenroll.mjs
```

---

## Plans

| Plan | Price | Quota |
|------|-------|-------|
| Free (Autonomous) | $0 | 500/day |
| Starter | $19/mo | 100K/mo |
| Pro | $49/mo | 300K/mo |
| Business | $199/mo | 2M/mo |
| Enterprise | Contact us | Custom |

---

### Contact & Support

- **Email**: thomas@openguardrails.com

---

## Update MoltGuard

To update MoltGuard to the latest version:

```bash
# Update the plugin
openclaw plugins update moltguard

# Restart to load the updated version
openclaw gateway restart
```
---

## Uninstall

```bash
node ~/.openclaw/extensions/moltguard/scripts/uninstall.mjs
```

This removes MoltGuard config from `openclaw.json`, plugin files, and credentials. Restart OpenClaw to apply.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →