ClawHub
Back to skill

Security audit

qa-tech-selection

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent QA tool-selection guide, but it recommends an unpinned external skill-bundle install that could change the agent's behavior beyond this skill.

Install this only if you are comfortable with a Chinese-language QA selection skill and avoid running the recommended external `npx skills add Kokxi/qa-test-skills` command unless you first verify the source, pin a specific version or commit, and understand the additional skills it will add.

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to match common, ambiguous requests like 'tool choice' or 'framework choice', which can cause the skill to activate in contexts beyond QA tooling selection. Over-broad activation is dangerous because it increases unintended tool use, may override a more appropriate skill, and can expose users to the skill's embedded instructions such as external install guidance when not contextually justified.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs users to run npx skills add Kokxi/qa-test-skills without pinning an exact package version or immutable source reference. This creates a supply-chain risk: a future compromised or maliciously updated package could be fetched and executed at install time, and the surrounding text frames it as a recommended setup step, increasing the chance of unsafe execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language description includes substantial Chinese content followed by an English usage sentence, but does not state whether the skill should respond in the user's preferred language. This can create an implicit language policy mismatch for users who did not opt into mixed-language behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.