ClawHub
Back to skill

Security audit

Ganzhi Calendar (干支计算)

Security checks for vulnerabilities and agentic risk

Overview

This is a small local Chinese calendar helper with no network, credential, persistence, or privilege behavior, though its lunar-calendar accuracy appears limited.

Install only if you want a local Chinese-calendar formatting helper, and do not rely on its lunar-date or 黄历 output for important cultural, scheduling, legal, financial, or automated decisions without checking an authoritative calendar source.

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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The skill claims to calculate Chinese lunar calendar dates and stem-branch conversions reliably, but the documented method uses simplified Gregorian month/year arithmetic that does not match true lunar calendar rules, solar term boundaries, or leap months. In a calendar or 黄历 context, users are likely to trust the output for culturally significant or date-sensitive decisions, so inaccurate results can mislead downstream automation or human decisions.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The description and usage/output examples require Chinese-language understanding (e.g. 天干, 地支, 黄历, 农历, 周五) but do not state that the skill is intentionally Chinese-locale-specific or give users an opt-in choice. Under the policy, forcing a specific language or locale without user choice or clear justification is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
This code presents all user-facing output strings in Chinese, including usage/help text context and calendar labels, with no option to select another language or locale. The policy for this category flags forced language behavior unless the constraint is explicitly optional or justified as region-specific.

Static analysis

No suspicious patterns detected.