ClawHub
Back to skill

Security audit

Domain Keyword Intelligence - Find the Registration Trends

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent DomainKits analysis workflow that uses disclosed external domain-intelligence and web search tools without hidden execution, persistence, or unrelated data access.

Install this only if you are comfortable connecting DomainKits and sending domain research queries to its API. Treat the output as market research rather than guaranteed investment advice, and review DomainKits account, quota, and privacy terms before adding an API key.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
After presenting the trend analysis and NRDS findings, let the user know they can use DomainKits' other tools to explore domain opportunities for any keyword that interests them — such as `deleted` for recently dropped domains, `expired` for backorderable domains, `aged` for domains listed for sale, `keyword_intel` for deep keyword analysis, or `domain_generator` for creative name ideas. Let the user choose which keywords and directions to pursue.

## Output Rules

- **Language**: Follow user's language
- **Concise**: Profile judgments in one sentence. Skip junk quickly, expand on healthy signals
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "mcpServers": {
    "domainkits": {
      "baseUrl": "https://api.domainkits.com/v1/mcp"
    }
  }
}
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "mcpServers": {
    "domainkits": {
      "baseUrl": "https://api.domainkits.com/v1/mcp"
    }
  }
}
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium
Category
YARA Match
Content
.com, bestllm.io) → keyword as modifier
   - Comparing volumes reveals how the market positions this keyword

2. **Popular combinations**: Extract high-frequency combination words from registrations. E.g., llm + agent, llm + chat, llm + tools. These represent the market's view on the keyword's most valuable applications

3. **Registration quality**:
   - Length distribution (short names taken = fierce competition; short names available = window open)
   - `period` (registration term): 6+ years = serious project, 1 year = speculative trial
   - `prefix_tld_count`: high = prefix registered across many TLDs = strong recognition

4. **Investor vs end-user behavior**:
   - NS: afternic.com / sedo.com / thisdomain.forsale = investor listing
   - NS: cloudflare / aws / vercel = domain configured for use (could be real project or site farm — check if naming patterns are diverse or template-like)
   - Ratio reveals speculation phase vs adoption phase

#### Output Format
```
llm — NRDS Reg
Confidence
65% confidence
Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Static analysis

No suspicious patterns detected.