Back to skill

Security audit

qa-exploratory-testing

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent exploratory-testing skill with no hidden execution or data exfiltration behavior, though users should treat its optional unpinned install command cautiously.

Install this skill only if you want structured exploratory QA guidance. Do not paste real customer, payment, identity, or production data into sessions. Verify or pin the optional `npx` command before running it, especially because it installs a broader external skill set.

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
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description includes broad everyday trigger phrases such as '到处点一点' and '随机测试', which can cause the agent to invoke this skill in loosely related contexts. Over-broad activation increases the chance of unintended tool use, context switching, or applying this skill when a more appropriate and safer skill should be selected.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The when-to-use guidance mixes explicit keywords with broad situational criteria like '需要发现脚本化测试遗漏的问题、新产品快速验证时', making activation subjective and prone to accidental triggering. In agent systems, ambiguous routing rules can cause misselection of skills, leading to inappropriate workflows or unnecessary tool access.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill recommends running npx skills add Kokxi/qa-test-skills without pinning an exact package version or immutable source. This creates a supply-chain risk: a future malicious or compromised release could execute attacker-controlled install-time or runtime code when users follow the instruction.

Content

No source excerpt is available for this finding.