ClawHub
Back to skill

Security audit

BaZi

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed BaZi/feng shui reading skill with some broad routing language, but no hidden execution, persistence, credential use, or exfiltration behavior.

Before installing, be aware that the skill may ask for birth details, birthplace, focus areas like money or relationships, and optionally room photos or layout details. Use it as reflective entertainment or self-exploration, not as a basis for medical, legal, financial, or major life decisions, and confirm explicit BaZi/feng shui intent if a prompt seems like ordinary advice-seeking.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description uses broad activation phrases such as general interest in 'practical advice', 'cleaner intake/question flow', and combined feng shui/BaZi framing, which could cause the agent to invoke this skill for loosely related conversations. Overbroad routing increases the chance that users are steered into astrology-style guidance when they did not explicitly request it, creating misfires and inappropriate handling of sensitive topics like money, relationships, or health-adjacent questions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation examples include very broad phrases such as 'Give me the full read' and 'What should I change in my life and my space?', which can overlap with ordinary user conversation and cause the skill to activate when the user did not clearly request a BaZi/feng shui reading. This is not overtly malicious, but it increases the chance of unintended routing, privacy-relevant overcollection of birth/location/room details, and confusing responses outside the intended domain.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.