PromptDome

Integrate PromptDome prompt injection screening into OpenClaw. Use when setting up automatic protection against prompt injection, jailbreaks, and PII exfiltr...

Security Scan

The skill is internally consistent with its stated purpose (prompt-injection screening) but it sends incoming messages to a third-party API and stores your API key and short message previews locally — consider the privacy implications before installing.

Purpose & Capability

Name/description match implementation: hook auto-scans incoming messages and a plugin exposes promptdome_scan. Required binaries (curl, python3, openclaw) and PROMPTDOME_API_KEY are appropriate for contacting the external PromptDome API.

Instruction Scope

SKILL.md and setup.sh instruct the agent to copy hook and plugin files into ~/.openclaw, enable the hook, and persist the API key in openclaw.json. The handler and plugin both send message text to the PromptDome API (expected), and the handler writes a preview (up to 80 characters) of messages to ~/.openclaw/logs/promptdome-gate.log (this logs potentially sensitive content).

Install Mechanism

No remote code downloads or extract operations; install is instruction-only and the provided setup.sh copies local files into ~/.openclaw. The runtime does contact the external API endpoint (promptdome.cyberforge.one) which is expected for the service.

Credentials

Only PROMPTDOME_API_KEY (and optional PROMPTDOME_API_URL) are required — proportionate to purpose. However, the key is persisted in openclaw.json in plaintext by the setup script and used as a bearer token when sending message content to the third-party API; you should treat this credential as sensitive.

Persistence & Privilege

always:false and the skill does not request elevated platform privileges. The setup script enables the hook and writes to the agent's config (openclaw.json) and to ~/.openclaw/logs, which is reasonable for a plugin of this nature.

Assessment

This skill appears to implement what it advertises, but installation will cause your incoming messages to be sent to a third-party API (https://promptdome.cyberforge.one by default). The setup script stores your PROMPTDOME_API_KEY in ~/.openclaw/openclaw.json and the hook writes short message previews to ~/.openclaw/logs/promptdome-gate.log — both may contain sensitive information. Before installing: (1) confirm you trust the PromptDome service and review its privacy/data-retention policy, (2) avoid enabling this on agents that handle highly sensitive or regulated data unless you self-host the endpoint (PROMPTDOME_API_URL override), (3) consider rotating the API key and restricting access to openclaw.json, (4) test on non-sensitive data first, and (5) only allow the promptdome_scan tool to agents you explicitly trust (use the tool allowlist).

PromptDome × OpenClaw

API key required — Get yours free at https://promptdome.cyberforge.one/dashboard/api-keys (Sign up → Dashboard → API Keys → Create Key)

Adds automatic prompt injection detection to any OpenClaw agent. Two components work together:

Component	What it does	When it fires
promptdome-gate hook	Auto-scans every incoming message; injects ⚠️ warning if injection detected	Every message:received — zero agent code required
promptdome_scan tool	Explicit scan agent can call on any content	On demand — web content, files, tool outputs

---

Quick Setup (60 seconds)

bash skills/promptdome/scripts/setup.sh --api-key sk_shield_live_YOUR_KEY

That's it. The script:

1. Tests your API key against the PromptDome API
2. Installs promptdome-gate hook → ~/.openclaw/hooks/promptdome-gate/
3. Installs promptdome_scan plugin → ~/.openclaw/extensions/promptdome/
4. Saves API key to openclaw.json env block
5. Enables the hook automatically
6. Prompts you to restart the gateway

Get an API key: https://promptdome.cyberforge.one/dashboard/api-keys

---

Manual Setup

1. Copy files

# Hook (auto-scanning)
mkdir -p ~/.openclaw/hooks/promptdome-gate
cp skills/promptdome/hook/HOOK.md   ~/.openclaw/hooks/promptdome-gate/
cp skills/promptdome/hook/handler.ts ~/.openclaw/hooks/promptdome-gate/

# Plugin (explicit tool)
mkdir -p ~/.openclaw/extensions/promptdome
cp skills/promptdome/plugin/index.ts ~/.openclaw/extensions/promptdome/

2. Set API key

Add to ~/.openclaw/openclaw.json:

{
  "env": {
    "PROMPTDOME_API_KEY": "sk_shield_live_YOUR_KEY"
  }
}

Or set PROMPTDOME_API_KEY in your shell environment.

3. Enable hook and restart

openclaw hooks enable promptdome-gate
openclaw gateway restart

---

What Happens After Install

• Every incoming message → scanned automatically before the model processes it
• BLOCK (score ≥ 70): [PROMPTDOME BLOCK] warning injected into conversation
• WARN (score ≥ 40): Soft caution note injected
• ALLOW: Silent — no overhead in conversation history
• Scan log: ~/.openclaw/logs/promptdome-gate.log
• Fail-open: if API is unreachable, messages pass through unblocked

---

Using the Agent Tool

Enable promptdome_scan in your agent's tool allowlist:

{
  "agents": {
    "list": [{ "id": "main", "tools": { "allow": ["promptdome_scan"] } }]
  }
}

Then agents call it like any tool — before processing web fetches, search results, uploaded files, or any external content.

---

Self-Hosted PromptDome

Override the API endpoint:

{
  "env": {
    "PROMPTDOME_API_KEY": "sk_shield_live_...",
    "PROMPTDOME_API_URL": "https://your-instance.com/api/v1/shield"
  }
}

---

Detection Coverage

PromptDome engine covers 32 attack categories including:

• Prompt injection & jailbreaks
• Fake system events / gateway spoofing
• PII & credential exfiltration
• ClickFix / social engineering
• HTML/DOM injection (browser agents)
• Agentic chain poisoning
• Multilingual evasion (18 languages)

Full category list: https://promptdome.cyberforge.one/docs