ClawHub
Back to skill

Security audit

Meihua Yijing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Chinese divination helper that runs a local Python script and does not show hidden access, persistence, network use, or destructive behavior.

Install this if you want a Chinese-language Mei Hua Yi Jing divination helper. Treat the output as entertainment or cultural reference only, and be aware that it may answer in Chinese unless the agent translates or adapts the response.

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
  • 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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The description says the skill performs 梅花易数 divination based on time, numbers, or direction, but it does not specify concrete trigger phrases, scope limits, or negative examples. In a manifest/markdown context, this makes activation conditions ambiguous and could overlap with ordinary requests involving time, numbers, or directions.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill content is written entirely in Chinese and directs the agent as a 梅花易数 expert without indicating that language should follow user preference. This can violate language/locale policy when the user has not opted into Chinese output.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
This Python file contains natural-language descriptions and user-facing output exclusively in Chinese, including the module docstring and all command output. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly justified as region-specific.

Static analysis

No suspicious patterns detected.