ClawHub
Back to skill

Security audit

China Phone Checker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple documented wrapper for an external phone-number lookup API, with privacy considerations users should understand before use.

Install only if you are comfortable sending queried phone numbers and your apipick API key to apipick.com. Use the APIPICK_API_KEY environment variable rather than pasting credentials into chat, and only look up numbers you have permission to submit to a third-party service.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README explicitly instructs users to send phone numbers to a third-party API but does not warn that the queried numbers will be transmitted off-platform or discuss privacy, retention, or consent considerations. Phone numbers are personal data, so omitting this disclosure can lead to unintended sharing of sensitive user information and noncompliance with privacy expectations or policy requirements.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends both a user-provided phone number and an API credential to a third-party service, but the description does not clearly warn the user about that external disclosure. This can lead users to share sensitive personal data or secrets without informed consent, especially because phone numbers are personal data and the API key is a credential tied to the user's account.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The API reference explicitly instructs sending a phone number to a third-party service, but it provides no user-facing privacy notice, consent requirement, or data-handling warning. Because phone numbers are personal data and the skill is designed to transmit them externally, this creates a real privacy and compliance risk if users are not clearly informed before submission.

External Transmission

Medium
Category
Data Exfiltration
Content
### Example

```bash
curl -X POST https://www.apipick.com/api/check-china-phone \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{"phone_number": "13800138000"}'
Confidence
92% confidence
Finding
The example shows outbound transmission of a user-supplied phone number to an external endpoint, which is expected for the skill's function but still represents a real data egress path. In this context, the danger is not hidden code execution but the exposure of personal data to a third party without clear guardrails, notice, or consent mechanisms.

Static analysis

No suspicious patterns detected.