ClawHub
Back to skill

Security audit

miaoying-cli-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Miaoying CLI integration for creating forms, QR codes, and exports, with some credential and personal-data handling that users should understand before use.

Install only if you intend to use the Miaoying third-party service. Prefer MIAOYING_API_KEY in an environment variable over the plaintext config file, avoid using it on shared machines, and treat exports or displayed submission results as potentially sensitive personal data.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Scope Creep

High
Confidence
95% confidence
Finding
The skill instructs use of a self-deactivation API endpoint that is not declared in the network allowlist. Undeclared network actions are dangerous because they bypass expected review boundaries and can let the skill perform impactful account actions that users and policy engines did not authorize.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger conditions are broad enough to match many ordinary 'collect information' or 'create a form' requests, increasing the chance the skill is invoked automatically in contexts where users did not intend third-party API use, local credential storage, or QR-login flows. Mis-triggering a networked skill with credential-management behavior can lead to unnecessary data exposure or unintended account actions.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The function retrieves and prints registration records that may contain personal data such as user identifiers, names, submission times, and free-form results. In a form/registration skill, those results can easily include sensitive user-submitted information, and displaying them directly to the terminal without masking, minimization, or an explicit privacy warning increases the risk of unintended disclosure to operators, logs, screenshots, or shared environments.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The code persists the API key in plaintext under the user's home directory without warning, consent, or any filesystem permission hardening. This creates credential exposure risk from other local users, malware, backups, or accidental disclosure, especially because the key appears sufficient for authenticated API access.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
src/commands/login.js:132