Back to skill

Security audit

qa-ci-cd-testing

Security checks for vulnerabilities and agentic risk

Overview

This is a CI/CD testing guidance skill with disclosed, mostly advisory behavior and no evidence of hidden execution, persistence, exfiltration, or destructive actions.

Installers should treat this as an advisory CI/CD testing skill. Review the optional unpinned `npx skills add Kokxi/qa-test-skills` command before using it, and only apply any deployment or release recommendations in environments where you have explicit authorization and rollback plans.

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
  • 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
92% confidence
Finding

The manifest description and when-to-use guidance are written as Chinese-only activation phrasing, which creates a natural-language locale constraint for skill invocation. The file does not indicate that this is a China-specific or Chinese-only skill, nor does it offer users an explicit language opt-in or alternative.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs users to run npx skills add Kokxi/qa-test-skills without pinning an exact package version or immutable source. This creates a supply-chain risk because future package updates or a compromised upstream release could cause different code to be fetched and executed than the author originally intended.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file states that the skill only writes evaluation files under workspace/, but later guidance discusses release, deployment, gray rollout, rollback, and production-adjacent operational actions. This mismatch can mislead operators about the skill’s real-world effect surface, causing unsafe trust decisions or use in more sensitive environments than intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file title and instructional text are entirely in Chinese and provide no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language context. Under the policy rules, a fixed language requirement without opt-in or justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.