ClawHub
Back to skill

Security audit

Baizhi Cloud Agent Toolkit

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a scoped Baizhi/OOMOL connector, but its fallback setup tells the agent to run a remote installer directly, which warrants review before use.

Before installing, review the OOMOL CLI installation path yourself and prefer a verified installer or package-manager method. Once installed, the skill appears intended for Baizhi web search and page-reading tasks, but remember that calls may consume credits and webpage results are untrusted content.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs users to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This is dangerous because it executes unverified code from the network immediately, enabling supply-chain compromise, MITM-related risk if trust anchors are subverted, or accidental execution of malicious installer changes with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says to use this skill for "ANY Baizhi Cloud Agent Toolkit request," which is a very broad activation condition without boundaries or negative examples. While domain-scoped, it still leaves unclear exactly which user requests should or should not invoke the skill, increasing the chance of unintended activation whenever Baizhi is mentioned.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.