ClawHub
Back to skill

Security audit

qa-combination-strategy

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only QA testing guidance skill; the main thing to watch is an optional unpinned install command for a larger skill bundle.

Before installing, review whether you want a primarily Chinese QA workflow skill. Do not paste real customer, payment, identity, or production data into examples. Only run the optional `npx` command for the larger skill bundle after verifying the publisher/source and preferably pinning a reviewed version.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest content is written as user-facing operational guidance entirely in Chinese, including trigger phrases, input/output expectations, and workflow instructions, while not indicating that other languages are supported or that the user may choose a locale. This creates a language policy concern because the skill appears to assume a specific language by default without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description and when-to-use fields include broad activation phrases such as '需要简化测试组合' and '参数多环境多时', which can overlap with many general testing discussions rather than clearly delimiting this skill's scope. The file provides positive examples but no exclusion conditions or negative examples to distinguish combinatorial-testing cases from ordinary test design requests.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill instructs users to install a package via npx skills add Kokxi/qa-test-skills without pinning an exact version. This can lead to supply-chain risk because a later compromised or incompatible package version could be fetched and executed implicitly at install time.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description repeatedly emphasizes combinatorial reduction and explicitly says not to try full coverage, framing the skill as a minimization strategy. However, the error-recovery guidance says to '回退到全组合方案', which directly conflicts with that stated intent rather than merely adding implementation detail.

Content

No source excerpt is available for this finding.