Security audit

Frontend Testing

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only frontend testing guidance skill with no hidden execution, persistence, or data access behavior.

Install if you want a Chinese-oriented frontend testing helper. Review the trigger wording if you maintain the skill, because generic testing or coverage requests may activate it more often than intended.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The invocation guidance says to enable the skill when the user mentions "提高覆盖率" (improve coverage), which is broad and can overlap with many general engineering discussions rather than clearly signaling a frontend-testing request. The file also does not provide exclusion conditions or negative examples to clarify when this phrase should not activate the skill.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The skill content is written to operate in Chinese and presents Chinese-only trigger examples without indicating language adaptation based on the user's preferences. This can override the user's expected language or steer interactions into a language they did not request, which is a prompt-quality and control issue rather than a direct code-execution risk.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrases are broad enough to match many ordinary requests such as 'write tests' or 'Jest/Vitest', which can cause this skill to activate when the user did not specifically ask for frontend-testing help. Over-broad activation can route unrelated work through the wrong skill, producing inappropriate guidance, reducing user control, and creating opportunities for prompt-shadowing if a competing skill is more sensitive or better scoped.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The name, tagline, and description all require Chinese, and the file does not indicate that users can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: The skill description and usage instructions are primarily written in Chinese, and the file does not state that users may choose another language or locale. This can be a language policy concern if the organization expects skills not to force a specific language without user opt-in.

Static analysis

No suspicious patterns detected.