Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 5. 如需本卦、变卦的原文、象辞、爻辞与白话基础释义，先按需读取 [references/zhouyi-64-gua.md](./references/zhouyi-64-gua.md)。
Security audit
易经起卦
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently performs I Ching divination with a local script and disclosed web lookup, and I found no hidden persistence, credential access, or destructive behavior.
Install only if you want a Chinese-first I Ching divination workflow. It runs a bundled Python script and may perform web searches for hexagram references, so keep personal, medical, financial, or relationship details out of search-sensitive prompts unless you are comfortable with that exposure.
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
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (13)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 5. 如需本卦、变卦的原文、象辞、爻辞与白话基础释义，先按需读取 [references/zhouyi-64-gua.md](./references/zhouyi-64-gua.md)。
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 5. 如需本卦、变卦的原文、象辞、爻辞与白话基础释义，先按需读取 [references/zhouyi-64-gua.md](./references/zhouyi-64-gua.md)。
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The README describes the skill in very broad terms such as handling natural-language divination requests automatically, without narrowly defining when it should activate. In an agent ecosystem, overly broad activation language can cause unintended invocation on loosely related queries, leading the agent to run local scripts and perform network lookups when the user did not explicitly request this skill.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The 'As a Skill' section says users can load the project and 'directly use natural language to ask,' but it does not constrain invocation to specific intent boundaries. That increases the chance that a general user message will be interpreted as a trigger for this skill, causing unnecessary script execution and external retrieval based on ambiguous input.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The English usage text repeats the same broad trigger model: after loading the skill, the user may 'simply ask questions in natural language.' In a shared agent environment, this can overmatch ordinary conversation and lead to accidental invocation of a tool-using workflow, including local execution and online searching, beyond user expectations.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly directs the agent to perform online research after receiving a user’s divination question, but it provides no privacy guardrails about sending potentially sensitive personal topics to third-party services. Because divination prompts often involve health, relationships, finances, or employment, this can lead to unintended disclosure of sensitive user content to external systems.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The natural-language instruction in the default prompt is written as an imperative in English and directs the interaction flow without indicating that the user may choose another language. This can violate a language/locale policy when the skill is otherwise presented in Chinese and does not document any opt-in or locale justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The document title and instruction '组织最终回答时使用本文件' establish a required response format entirely in Chinese, and the rest of the file consistently prescribes Chinese-language output conventions. This is a natural-language policy concern because it forces a specific language without any user opt-in or stated region-specific justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
该 markdown 文件整体以中文编写，并在用途与使用说明中默认作为 skill 的本地参考文档使用，未见任何允许用户选择语言/locale 的说明。按规则，强制单一语言且无用户选择或明确地域限定，属于自然语言层面的语言/地区策略风险。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The instruction says to answer in Chinese unless the user requests otherwise. This sets a default language choice without explicit user opt-in, which can conflict with policies requiring language preference to be chosen by the user unless clearly justified.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
All user-facing guidance and the recommended reminder script are written only in Chinese, and the file provides no opt-in, alternative language path, or justification that the skill is intended solely for Chinese-speaking users. This can amount to a language/locale policy issue when the skill is used in broader contexts.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This Python file contains user-facing prompts and printed results exclusively in Chinese, such as the input prompt and all result labels. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a locale/language policy issue.
- Content