ClawHub
Back to skill

Security audit

Miniprogram Development

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WeChat Mini Program development helper with expected file, command, and API capabilities, but no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you want an agent to help with WeChat Mini Program development. Keep API keys in environment variables, use a sandbox or project checkout, and require confirmation before commands that publish, modify many files, or interact with external services.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description uses broad activation language such as using it whenever code generation, debugging, testing, or deployment is needed, without a clear invocation boundary or scoped consent. In an agent ecosystem, this can cause the skill to be auto-selected in situations the user did not explicitly intend, increasing the chance of unexpected command execution, file writes, or external interactions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill exposes powerful tools (read, write, exec, API usage) and discusses automation, file handling, and command execution, but it does not present a prominent upfront warning that operation may execute commands, modify files, and contact external services. Users and orchestrators may therefore invoke it without informed consent, creating risk of unintended side effects, data exposure, or unsafe execution in sensitive environments.

Static analysis

No suspicious patterns detected.