Back to skill

Security audit

Liuyao Yijing — 六爻易经占卜

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese divination skill with limited local preference memory and no executable code or external API behavior.

Install only if you want a Chinese-language Liuyao/Yijing divination assistant. Be aware it may remember explicit preferences such as divination method or response style in a local MEMORY.md file, and do not treat its finance, health, legal, or life-decision readings as professional advice.

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
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes broad natural-language phrases such as “帮我起一卦”, which can plausibly appear in casual conversation without strong domain constraints. This can cause the skill to activate unexpectedly, increasing the chance that users are routed into fortune-telling behavior when they did not clearly intend it, especially in mixed-topic chats.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly reads from and writes to persistent MEMORY.md files containing user preferences, but the main description does not clearly warn users that persistence is occurring. This creates a privacy and consent risk because users may disclose sensitive preference or behavioral information without understanding it will be retained across sessions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Line L003 states that divination must strictly follow the tables in this file, and the entire skill file is presented only in Chinese with no indication that users may choose another language or locale. Under the policy rule for natural-language violations, forcing a specific language without opt-in is a reportable issue unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The skill description, examples, and operating instructions are written entirely in Chinese and present Chinese trigger phrases only, implying a fixed language expectation. There is no indication that users may choose another language or that the locale restriction is intentional and justified as a region-specific tool.

Content

No source excerpt is available for this finding.