Security audit

AI 测试盲区补偿

Security checks for vulnerabilities and agentic risk

Overview

This is a QA helper skill that reads test artifacts and suggests additional test cases, with no hidden execution, persistence, or data exfiltration behavior found.

Install this only if you want a Chinese-language QA workflow helper that can read your provided test and requirement files to suggest missed scenarios. Review the separate full-suite npx install recommendation before running it, since this inspected skill itself does not validate that larger package.

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 (2)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The activation text says the skill 'automatically activates after AI output review' and also lists broad phrases such as '全面覆盖', '是不是不够', and '哪还没测'. These phrases can occur in normal testing discussion and the file does not provide scope limits or negative examples clarifying when the skill should not trigger.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill metadata and instructional content are entirely in Chinese, including the display name and all invocation phrases, with no indication that users may choose another language. For a general QA skill, this can amount to an implicit language policy constraint without opt-in or documented regional justification.

Static analysis

No suspicious patterns detected.