ClawHub
Back to skill

Security audit

Bazhuayu

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Bazhuayu connector wrapper with read and write actions, and its higher-impact actions require user confirmation.

Install this if you trust OOMOL's connector model and want your agent to manage Bazhuayu through your connected account. Review payloads carefully before approving write actions such as starting tasks, stopping tasks, copying tasks, updating parameters, or marking data exported.

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 (1)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The description says to use this skill for ANY Bazhuayu request and instead of calling the API directly, which can cause the agent to invoke a Bash-capable skill on very broad mentions. Because the skill includes both read and state-changing actions, overly broad routing increases the chance of unintended execution paths, especially if downstream prompts or user requests are ambiguous.

Static analysis

No suspicious patterns detected.