Security audit

六爻纳甲技能

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese divination calculator with no hidden system access, but users should not treat its health, financial, legal, or safety-related outputs as professional advice.

Install only if you want a Chinese-language cultural/divination tool. Treat all health, investment, lawsuit, pregnancy, travel, and other consequential readings as entertainment or cultural interpretation, not as professional guidance or a basis for real-world decisions.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The README explicitly presents '健康' as a supported question type and frames outputs as diagnostic-style divination ('疾病、医药', '吉凶判断') without any disclaimer that results are not medical advice. In a user-facing skill that automates analysis, this can encourage users to substitute superstition for professional medical evaluation, creating foreseeable safety risk through delayed or avoided care.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The natural-language content in the description, title, quote, and example question is exclusively Chinese, which effectively forces a specific language for users. The file does not indicate that the skill is region-specific or provide an opt-in or alternative language, so this is a language/locale policy concern.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: L376 的方法名和 L377 的注释表明该函数应根据动爻生成变卦，但实际实现仅保留占位逻辑：L381-L388 未完成阴阳变换，L390 明示“简化”，多数路径最终在 L400 返回“待计算”。这与技能说明中支持“动爻变卦”及自动化断卦分析的意图形成直接背离。
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill produces authoritative-sounding divination conclusions, scores, and behavioral recommendations such as 吉凶判断, 建议, and 趋避 without any disclaimer that the output is interpretive entertainment rather than dependable advice. In contexts involving health, legal matters, travel, investment, or other consequential decisions, users may rely on this output and suffer real-world harm from misleading or unjustified recommendations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The README content, usage instructions, parameter descriptions, and output examples are all presented only in Chinese, which effectively forces a specific language for users. The policy allows locale constraints when they are explicitly documented and justified or when users are offered a choice, neither of which is present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Natural-language strings throughout the interface, including parser descriptions and printed output, are exclusively in Chinese. The policy requires avoiding forced language/locale constraints unless the user is given a choice or the locale restriction is clearly justified, which is not present in this file.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.