ClawHub
Back to skill

Security audit

bazi-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language Bazi analysis helper that runs a local calculation script and does not show hidden data access, exfiltration, persistence, or destructive behavior.

Install only if you are comfortable providing birth date, birth time if known, and gender for a local traditional-culture/entertainment analysis. Expect it to create ~/.venvs/bazi and install lunar_python; treat outputs as entertainment, not decision advice.

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
95% confidence
Finding

The activation criteria are extremely broad, including any mention of fortune-telling, birth dates, or loosely related phrases, which can cause the skill to trigger in conversations that are not actually requesting this capability. Over-broad routing increases the chance of inappropriate collection of sensitive personal data such as birth date, time, and gender, and may divert unrelated conversations into a pseudoscientific analysis flow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The top-level docstring, CLI help text, argument choices, and output strings are all hard-coded in Chinese, and gender/focus inputs are restricted to Chinese values such as '男'/'女' and '综合'. This creates a locale policy concern because the skill imposes a specific language on all users with no opt-in, fallback, or explanation that it is intended only for a Chinese-language audience.

Content

No source excerpt is available for this finding.