ClawHub
Back to skill

Security audit

ZAI Coding Plan Usage

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Z.ai usage checker that reads a Z.ai API key and calls fixed usage endpoints, with no evidence of hidden persistence, destructive behavior, or unrelated data access.

Install this only if you want an agent to query your Z.ai usage using the Z.ai API key already present in OpenClaw or in ZAI_API_KEY/ZHIPU_API_KEY. Expect it to send authenticated requests to open.bigmodel.cn and display account usage details; it does not show evidence of modifying your account or installing background behavior.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill invokes a local Node.js script and states that an API key is read from config or environment variables, but it does not declare any explicit tool scope or permissions. This creates an under-specified trust boundary: the skill can access sensitive environment-based secrets or broader runtime capabilities without transparent restriction, increasing the risk of unintended secret exposure or overbroad execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code accesses sensitive credentials by reading a local auth-profiles.json file and falling back to environment variables. Although comments describe the behavior for developers, there is no user-facing prompt or warning in runtime output that the script will access stored API keys, which matches the missing-warning criterion for code files handling credentials.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The HTTP request hard-codes an Accept-Language header of 'zh-CN,zh', which imposes a specific locale regardless of user preference. This is a natural-language policy concern because the file does not offer opt-in, configuration, or justification for forcing Chinese locale behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.