Security audit

找月嫂

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a coherent moon-sitter booking workflow, but it handles sensitive personal and SMS verification data with under-disclosed backend routing and logging concerns.

Review this before installing if you are comfortable sending phone number, SMS verification code, due date, city, service period, and budget to the provider’s hardcoded backend. The behavior is not clearly malicious, but the backend disclosure mismatch and logging of verification requests make it appropriate for Review rather than automatic trust.

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 (2)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The documented workflow sends phone numbers and SMS verification codes to a remote backend without any privacy disclosure, consent language, or warning about data handling. Because SMS codes are authentication secrets and phone numbers are personal data, collecting and transmitting them without clear notice can expose users to privacy harm, account-linkage risk, and uninformed consent.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The lead-submission command transmits personal data such as phone number, city, due date, and budget to an external service without disclosing sharing, retention, or downstream use. In this skill context, these fields can reveal sensitive family and pregnancy-related information, making undisclosed collection more privacy-impactful than generic contact collection.

Static analysis

No suspicious patterns detected.