ClawHub
Back to skill

Security audit

Bazi Pan

Security checks for vulnerabilities and agentic risk

Overview

This skill runs a local Chinese astrology chart script with no network, persistence, credential access, or hidden system changes, though its documentation overstates some calculation features.

Install only if you are comfortable sharing birth date and time with the local agent workflow, and treat the astrology output as entertainment or reference. Do not rely on this skill for precise lunar-calendar conversion or annual fortune analysis unless the implementation is corrected.

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 (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The skill’s documented behavior promises lunar-date input, annual luck/流年 analysis, and accurate script-based chart generation, but the shown invocation only passes four numeric arguments and provides no visible lunar-to-solar conversion or 流年 computation. This creates a trust and integrity problem: users may rely on outputs as accurate divination/analysis when the implementation likely omits required logic, leading to systematically incorrect results presented as authoritative.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
This Python skill hardcodes Chinese-language descriptions, prompts, usage text, and output, which effectively forces a specific language on users. The file does not provide any opt-in, alternate locale, or documentation that the skill is intentionally limited to Chinese-speaking users.

Static analysis

No suspicious patterns detected.