汲取百家所长的最强算命大师 - Zhouyi - Yijing - Zhanbu - Bagua - Xuanxue -Shushu - Witch - Fortune Teller _占卜_周易_易经_八卦_玄学_术数

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 7:18 AM UTC
• Version: 1.0.0

Overview

This is a local Zhouyi/I Ching divination and lookup skill; its main behaviors match its stated purpose and do not show exfiltration, hidden execution, or destructive actions.

Install only if you are comfortable with a Chinese-language local Zhouyi tool. Avoid entering highly sensitive health, financial, legal, or relationship details on shared browsers, because recent questions are saved locally until cleared. Treat readings as reflective guidance, not professional advice.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (27)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The declared purpose describes an end-user divination product centered on Zhouyi content and interaction quality. The supplied code chunk does not implement divination, hexagram logic, scripture presentation, or any user-facing I Ching functionality. Instead, it is a release engineering script for bumping versions and packaging the project for publication. That is a materially different primary purpose from the declared description, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The declared description presents a user-facing Zhouyi/I Ching divination product with curated original-text content, interaction design, and rule presentation. The supplied code does not implement divination, text presentation, casting flow, or interpretation. Instead, it is a verification test for a catalog of systems, asserting metadata completeness and status values for various items. This is a materially different primary purpose from the declared skill behavior, so it should be flagged as a mismatch.

Content

No source excerpt is available for this finding.

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md

node scripts/zhouyi_cli.js cast --question "我是否该推进这次合作" --method coin --json

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md

node scripts/zhouyi_cli.js cast --question "我是否该推进这次合作" --method coin --json

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md

node scripts/zhouyi_cli.js cast --question "我是否该推进这次合作" --method coin --json

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md

node scripts/zhouyi_cli.js cast --question "我是否该推进这次合作" --method coin --json

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md

node scripts/zhouyi_cli.js cast --question "我是否该推进这次合作" --method coin --json

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

md

node scripts/zhouyi_cli.js cast --question "我是否该推进这次合作" --method coin --json

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 99)May include surrounding context.

md

node scripts/zhouyi_cli.js cast --question "我是否该推进这次合作" --method coin --json

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

md

node scripts/zhouyi_cli.js cast --question "我是否该推进这次合作" --method coin --json

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 149)May include surrounding context.

md

node tests/verify_zhouyi_system.js

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 150)May include surrounding context.

md

node tests/verify_system_catalog.js

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence

Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The '何时使用' section says to prioritize this skill whenever users express needs like '帮我起一卦' or '用周易看一下这件事', but it does not define exclusion conditions beyond a short list of unsupported systems. Some phrases are general enough in ordinary conversation that an agent could over-invoke the skill without clearer trigger constraints or negative examples about nearby but out-of-scope requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The manifest says to use the skill to cast a hexagram or look up source text, but it does not specify the exact trigger phrases, boundaries, or exclusion conditions for when the skill should activate. This broad invocation description could overlap with general discussions about the I Ching and lead to unintended activation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The default prompt instructs the skill to explain the result "in plain Chinese," which imposes a specific language on users. There is no indication that users may choose another language or that this locale restriction is optional or justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill's user-facing content and formatting are fixed to Chinese, including Chinese text strings throughout and an explicit "zh-CN" locale in date formatting. This forces a specific language/locale without any opt-in or alternate selection, which matches the stated natural-language policy violation criteria.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The manifest centers this skill as an I Ching / Zhouyi Benjing product that restores the canonical text and casting experience. However, this code actively recommends and presents other divination systems via routing logic, framing them as related systems for different question types rather than merely using them as background inspiration.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

Persisting divination questions and history in localStorage without a visible warning means users may unknowingly leave highly personal natural-language content on the device. In a divination context, prompts often contain intimate details about health, relationships, finances, and work, so undisclosed retention materially increases privacy risk.

Content

No source excerpt is available for this finding.

Ssd 3

Medium

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The app retains and re-displays sensitive user-supplied text, and also offers easy copying of the generated reading, increasing the chance that private content is exposed to other local users or to scripts with same-origin access. Since the stored journal includes raw questions and derived readings about intimate topics, the privacy impact is higher than for generic app state.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

This JavaScript catalog contains user-facing natural-language fields such as name, status, basis, capability, and guardrail exclusively in Chinese. Because the file does not indicate that the skill is region-specific or that users can opt into this locale, it may violate the language/locale policy against forcing a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

This code file contains user-facing natural-language strings that assume a Chinese-speaking user, including the usage text and subsequent output formatting throughout the CLI. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The code stores users' free-text questions and full reading history in localStorage, which persists across sessions and is accessible to any script running in the same origin. Because users may enter sensitive relationship, health, work, or financial questions, this creates a privacy exposure if the device is shared, the browser profile is inspected, or same-origin script compromise occurs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

This JavaScript file consists entirely of Chinese text literals for the dataset and does not indicate any user opt-in, language selection, or locale scoping. Under the policy rule for natural-language violations, hard-coding a single language without documented choice or justification can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The document declares lang="zh-CN", which sets a specific language/locale for the entire experience. Under the policy, forcing a specific language without offering the user a choice can be a natural-language locale violation unless clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.