ClawHub
Back to skill

Security audit

huawei-cloud-dcs-query

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-only Huawei Cloud DCS inspection helper, with credential-handling and trigger-scope cautions users should manage.

Install only if you need Huawei Cloud DCS read access. Use a least-privilege read-only IAM policy, avoid pasting real access keys into shared shells or scripts, rotate credentials as needed, and confirm the skill is being used only for intended Huawei DCS queries when the request mentions generic Redis resources.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger list includes broad phrases such as 'query DCS', 'show DCS', 'DCS instance', and 'Redis instance', which may match generic user requests and invoke the skill outside its intended scope. Overbroad activation can cause unintended access to sensitive operational metadata such as ACL accounts, IP whitelists, slow logs, tags, quotas, and instance details, increasing the chance of data overexposure or confusing tool selection.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The guide instructs users to set long-lived access keys directly via CLI commands and environment variables but provides no warning about secret handling, shell history, process exposure, or preference for short-lived credentials. In a cloud operations skill, this can lead to credential leakage and unauthorized access to Huawei Cloud resources if copied into terminals, scripts, or shared environments.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.