ClawHub
Back to skill

Security audit

Alibaba Cloud Model Setup

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a normal Alibaba Cloud setup helper, but its documented no-write and safety controls do not fully match the script while it handles API keys and changes persistent OpenClaw configuration.

Review before installing. Use it only if you want it to modify your OpenClaw configuration, avoid inline API key storage, do not rely on --list-models or --non-interactive as no-write safeguards in this version, and inspect the config and backup after running.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill advertises and instructs execution of file read/write, shell, and network-capable operations but does not declare permissions. This creates a trust and review gap: users or policy engines may approve the skill without understanding it will modify config files and make outbound requests.

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding
The documented behavior does not fully match the effective behavior: it changes default model settings, creates backups, performs live API-key validation requests, and the described site/model support appears inconsistent. This mismatch is dangerous because users may consent to a narrow provider setup task while the skill performs broader persistent changes and outbound network actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The example configuration shows an inline API key in a JSON file without a strong warning against secret-at-rest storage. This encourages insecure copying patterns that can leak credentials through backups, version control, local compromise, or accidental sharing of config files.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The document includes an inline API key storage example in `openclaw.json`, which can normalize placing long-lived secrets in plaintext configuration files. Even though it is labeled 'Not Recommended', it does not clearly explain the concrete risks such as accidental Git commits, local file disclosure, backup leakage, or exposure to other local users/processes.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
When the user selects inline key storage, the API key is written directly into the JSON config on disk. Storing secrets in plaintext configuration files increases exposure through backups, accidental commits, local file disclosure, or other processes/users reading the file, especially since the save path does not enforce restrictive permissions or strongly warn about the persistence risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.