Security audit

qa-question-framework

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only QA questioning template with no executable code, though users should treat its optional unpinned install suggestion cautiously.

Install this skill as a read-only QA template. Do not paste real customer, payment, identity, or production data into prompts; if you choose to run the optional broader `npx` install command, first verify the source and prefer a pinned version or trusted package reference.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description lists triggers such as '不知道该问什么', '怎么获取信息', '需求不清楚', and '需要澄清', which are generic phrases that can arise in many ordinary conversations beyond this skill's intended QA-test-design context. Although the file mentions testing-related purpose elsewhere, the trigger list itself does not provide exclusion conditions or negative examples to clearly limit when the skill should or should not activate.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The natural-language instructions, triggers, and usage metadata are written entirely in Chinese, which effectively constrains the skill to a specific language. There is no statement offering multilingual support, user opt-in, or a documented reason that the skill must be Chinese-only.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The when-to-use metadata includes broad phrases like '不知道该问什么', '怎么获取信息', and '需求不清楚', plus a general condition about communicating requirement details with PM/developers. This lacks clear boundaries for activation and does not specify negative cases, increasing the chance of unintended invocation for routine information-gathering requests.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 83% confidence
Finding: The skill recommends installing a remote package via npx skills add Kokxi/qa-test-skills without pinning a specific immutable version. That creates a supply-chain risk: a later compromised or maliciously updated package could execute unexpected code at install time or alter behavior for users who follow the instruction.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: Line L023 states a concrete operational guarantee about writing only to workspace/ and not persisting or sharing data. However, this skill file is purely a documentation/template artifact with allowed tools limited to Read/Grep/Glob and no implementation that writes files, so the statement about actual behavior contradicts what is present in the skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This markdown file presents all instructions and examples only in Chinese, with no note that the skill is Chinese-only or any option for other languages.
Content: No source excerpt is available for this finding.