ClawHub
Back to skill

Security audit

uniapp-test

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed uni-app testing workflow that edits test files and runs test commands, with some overbroad activation language users should notice.

Install this if you want an agent to help maintain uni-app automated tests. Be aware that the skill may edit page-adjacent test files and run npm test commands, including platform/device tests, so use it for explicit testing tasks and review changes before keeping them.

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 (4)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger conditions are extremely broad and include many common uni-app-related terms, which can cause the skill to activate in situations where the user did not intend to run a test-engineering workflow. Because the skill is empowered to inspect project files, create or modify *.test.js, and run commands, accidental invocation can lead to unnecessary file changes or command execution in unrelated conversations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation scope is extremely broad and auto-triggers on many common uni-app or testing-related terms, which can cause the skill to run in contexts where the user did not clearly request code modification or command execution. That increases the chance of unintended file edits, test execution, or environment interaction under ambiguous prompts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The workflow explicitly directs the agent to create or modify *.test.js files and run platform-specific commands, but it does not require an explicit user-facing confirmation before making changes or executing commands. In an agent setting, this can lead to unapproved workspace modifications or command execution that may consume resources, affect connected devices, or alter the project state unexpectedly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to create new test files or modify existing ones, but it does not clearly disclose up front that using the skill may write to the repository. In an agent environment, undisclosed write behavior increases the risk of surprising or unauthorized workspace modifications, especially when combined with broad triggering rules.

Content

No source excerpt is available for this finding.