ClawHub
Back to skill

Security audit

Miniprogram Development

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only WeChat Mini Program development skill whose requested file and command access is broad but disclosed and generally aligned with its development purpose.

Install this if you want AI assistance for WeChat Mini Program development. Because it declares command execution and write access, keep it scoped to the intended project directory, review generated changes, and require explicit confirmation before preview, publish, deployment, or any command that uses credentials.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation description is overly broad, describing generic code generation, debugging, testing, and deployment use cases without tight scoping to clearly defined Mini Program tasks. In an agent ecosystem, this can cause the skill to be invoked for general development requests, unnecessarily granting access to read/write/exec capabilities and increasing the chance of unsafe automation or command execution in contexts the user did not intend.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description states that the skill supports or should be used with Chinese interaction ('支持中文交互' / 'Use when ... 使用'), without making clear that language choice should follow user preference. This can cause unintended activation or prompt steering in multilingual environments, making the agent more likely to route requests here based on language cues rather than actual task fit.

Content

No source excerpt is available for this finding.