Security audit

易经占卜 I Ching Divination

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese-language Yijing divination skill with no network, credential, persistence, or privileged behavior found.

Install only if you want a Chinese-language reflective divination tool. Do not rely on it for financial, legal, medical, safety, or other high-stakes decisions; use qualified professional sources for those.

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)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The code substantially matches the divination-generation portion of the description: it supports 铜钱法 and a simplified 蓍草法, computes 本卦/互卦/变卦, and outputs structured results. However, the declared description also claims '提供Oracle Voice诠释' and implies interpretive guidance for users seeking 解读 or 决策指引. The supplied code contains no voice integration, no Oracle API usage, no text interpretation of hexagram meanings, and no explanatory reading logic beyond structural generation and visualization. Therefore, the description overstates key user-facing capabilities, creating a material description-behavior mismatch.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The README uses a concrete investment-decision example ('现在适合投资股票吗？') and presents the system as giving interpretive guidance, but it does not warn users that outputs are not financial advice. In this context, users may over-rely on divination output for real financial decisions, increasing the risk of harmful or manipulative decision-making even though no direct code-execution risk is present.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: The natural-language content of the skill README appears to assume a single language/locale throughout. Under the policy, forcing a specific language without user opt-in can be a language/locale policy violation unless the locale limitation is explicitly justified.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: This JSON dataset stores all user-facing textual content in Chinese, including names, judgements, images, oracle_voice, and keywords, with no indication that the skill is region-specific or that users can choose another language. That creates a natural-language policy concern under the language/locale rule because the file effectively hard-codes one language for outputs.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: This manifest-style JSON file contains a natural-language info string entirely in Chinese: "完整64卦数据位于 assets/hexagrams_full.json". Under the language/locale policy, forcing a specific language without user opt-in or documented justification can be a policy violation, and this file provides no indication that the locale restriction is intentional or user-selectable.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: This code file contains user-facing natural-language text entirely in Chinese, including the module description and command-line help, and the script emits result labels in Chinese-oriented terminology. The file does not offer any user opt-in or alternative locale, which matches the policy category for forced language/locale without choice.

Static analysis

No suspicious patterns detected.