What We Detect How It Works Pricing FAQ ← ClawOps Services Try Free Scan
1 Free Scan on Signup

ClawOps Shield

Prompt Injection Detection for OpenClaw

Paste a GitHub link, ClawHub skill, or any URL, or upload a local file. Our scanner detects prompt injection, data exfiltration, privilege escalation, and hidden malicious instructions before they reach your agent.

Prompt Injection Data Exfiltration Privilege Escalation Hidden Instructions Obfuscated Payloads
clawops-shield v1.0
$ shield scan weather-skill/SKILL.md

[1/5] ✓ No prompt injection patterns detected
[2/5] ✓ No data exfiltration URLs found
[3/5] ⚠ Mild concern: file reads from /etc/ path (line 34)
[4/5] ✓ No privilege escalation attempts
[5/5] ✓ No obfuscated or encoded payloads

RESULT: LOW RISK - 1 advisory, 0 critical, 0 high
Recommendation: Review line 34 /etc/ reference. Likely benign (config read).

$
47%
of community skills contain at least one advisory
12%
contain high or critical severity findings
5 sec
average scan time per file
23+
detection rules and growing

Every Attack Vector, Covered

Community skills and shared prompt files can contain hidden instructions that hijack your agent, steal your data, or escalate privileges. We catch all of it.

💥

Prompt Injection

Hidden instructions that override your agent's system prompt. Phrases like "ignore previous instructions," "you are now," role-swapping attacks, and multi-turn manipulation chains.

📦

Data Exfiltration

Commands that try to send your private data to external URLs. Detects suspicious fetch/curl/webhook calls, encoded URLs, and attempts to read and transmit sensitive files like API keys, tokens, or memory files.

🔒

Privilege Escalation

Attempts to gain elevated access, run shell commands, modify system files, change agent configurations, or break out of sandbox restrictions. Catches sudo, chmod, and system-level file writes.

👀

Hidden Instructions

Zero-width characters, invisible Unicode, comment-embedded commands, and instructions hidden in seemingly benign text. These are invisible to humans but executed by AI agents.

🧬

Obfuscated Payloads

Base64-encoded commands, hex-encoded strings, ROT13, URL-encoded instructions, and other encoding tricks designed to bypass simple pattern matching while still executing malicious actions.

🚧

Social Engineering

Prompts that manipulate the agent into revealing private information, bypassing safety guidelines, or performing actions the user never intended. Detects emotional manipulation and urgency tactics.

Three Steps to Safe Files

No setup, no CLI, no API keys. Upload your file, get your results, take action.

1

Share Your File

Paste a GitHub link, ClawHub skill URL, or any raw text URL. Or drag and drop a local file. Supports SKILL.md, AGENTS.md, SOUL.md, and any text-based prompt or config file. Files scanned in-browser, never stored.

2

Get Your Results

Within seconds, see a detailed breakdown of every finding. Each issue gets a severity level (Critical, High, Medium, Low), the exact line number, and an explanation of why it matters.

3

Fix With Guidance

Every finding comes with a specific remediation guide. Know exactly what to remove, replace, or flag. Copy the clean version or follow step-by-step instructions to sanitize the file yourself.

ClawOps Shield uses pattern-based detection to identify potential security threats. Results are informational only and may include false positives or false negatives. A clean scan does not guarantee a file is free from malicious content. Shield is not a substitute for professional security audits. See our Scanner Terms for full details.

Protect Your Agents. Pick Your Plan.

Every account gets 1 free scan. After that, pick the plan that fits your usage. Cancel anytime.

Starter
$5.99
per month
  • 10 scans per month
  • All 6 threat categories
  • Line-by-line analysis
  • Severity ratings
  • Remediation guidance
  • Email support
Get Started
Enterprise
$14.99
per month
  • Unlimited scans
  • All 6 threat categories
  • Line-by-line analysis
  • Bulk directory scanning
  • Custom rule definitions
  • API access for CI/CD
  • Team accounts (up to 5)
  • Exportable PDF reports
  • Dedicated support
Go Enterprise

Already a ClawOps client? Shield is included free with all ClawOps service plans. AI Receptionist, Revenue Ops, Custom AI Agents, and AaaS clients get unlimited scans at no extra cost.

Frequently Asked Questions

Can I scan files directly from GitHub or ClawHub?

Yes. Paste any GitHub URL (file, directory, or repo root), any ClawHub skill page link, or any raw text URL, and Shield will fetch and scan the file for you. No need to clone or download anything. Works with any public repository or skill listing. The file content is fetched and scanned entirely in your browser.

What file types can I scan?

Any text-based file: .md, .txt, .yaml, .yml, .json, .toml, .py, .js, .sh, and more. This covers SKILL.md, AGENTS.md, SOUL.md, USER.md, TOOLS.md, and any custom prompt or configuration file used by OpenClaw or similar agent frameworks.

Are my files stored on your servers?

No. All scanning happens client-side in your browser. Your file contents never leave your machine. When you scan from a URL, the file is fetched directly from the source (GitHub, ClawHub, etc.) to your browser and processed locally. We take privacy seriously, especially since these files can contain sensitive agent configurations.

What counts as a "scan"?

One file upload equals one scan. If you upload a ZIP or directory (Enterprise plan), each file inside counts as one scan. Re-scanning the same file after edits counts as a new scan.

How is this different from a regular code linter?

Code linters check syntax. Shield checks intent. We detect semantic attacks like prompt injection, social engineering, and hidden instructions that are valid text but designed to manipulate AI agents. Traditional linters would pass these without flagging anything.

I am a ClawOps client. Do I need to pay for Shield?

No. Shield is included free with every ClawOps service plan (AI Receptionist, Revenue Ops Sprint, Custom AI Agents, and Automation-as-a-Service). Just log in with the same account and you get unlimited scans.

Can I use this for non-OpenClaw files?

Yes. While optimized for OpenClaw skill files and agent configs, the detection rules apply broadly to any AI prompt file, LLM system prompt, or agent instruction set. If it tells an AI what to do, we can scan it.

Do Not Trust. Verify.

Every skill you install is a set of instructions your agent will follow blindly. Make sure those instructions are safe before they run.