ClawHub
Back to skill

Security audit

Miniprogram Dev Tool Free

Security checks across malware telemetry and agentic risk

Overview

The skill mostly looks like a WeChat miniprogram guidance tool, but it asks for write and command-execution authority while also containing mismatched, overly broad trigger instructions.

Review before installing. Use this only in a disposable or clearly selected miniprogram project workspace, and do not allow it to run commands or modify files unless you explicitly requested that action. The publisher should narrow the trigger text to WeChat miniprogram tasks and document what write and exec actions are allowed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Intent-Code Divergence

Medium
Confidence
94% confidence
Finding
The trigger conditions instruct the skill to activate for generic data analysis, reporting, statistics, and visualization tasks, which is unrelated to the stated miniprogram-development purpose. This kind of scope mismatch can cause the agent to route unrelated requests into a skill that also has read/write/exec capabilities, increasing the chance of unintended command execution or file modification in the wrong context.

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The skill declares exec and write tools even though the content is primarily guidance and best-practice documentation. Granting system-modifying capabilities beyond what is needed violates least privilege and becomes dangerous if the agent interprets broad instructions as permission to run commands, edit files, or otherwise affect the local environment.

Vague Triggers

High
Confidence
96% confidence
Finding
The trigger condition is overly broad and mismatched to the skill domain, instructing use for general data-analysis/reporting needs rather than miniprogram development. In an agentic environment, broad trigger text can cause accidental invocation on unrelated prompts, and because this skill exposes exec/write capabilities, misrouting can escalate into unsafe actions or confusing, unauthorized modifications.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill advertises write/exec capability but does not clearly warn users that it may modify files or run commands on the system. This lack of transparency is risky because users may expect passive guidance while the agent has authority to perform active, potentially system-changing operations.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.