Back to skill

Security audit

huaweicloud-config-helper

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed, read-only Huawei Cloud Config query helper, but users should treat its cloud inventory output and credentials carefully.

Install only if you intend to let the agent query Huawei Cloud Config inventory. Use a dedicated AK/SK with Config ReadOnlyAccess, avoid broad SELECT * or unscoped exports unless necessary, treat returned inventory as sensitive security data, and do not pass untrusted values into query parameters.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

High
Confidence
96% confidence
Finding
The trigger condition is extremely broad, stating the skill must be used for nearly any Huawei Cloud resource query, management, audit, or compliance scenario, even when Config is not explicitly mentioned. This can cause unintended invocation in loosely related contexts, leading to over-collection of cloud asset/configuration data and unexpected credential use.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents bulk querying of resource inventories, schemas, configurations, and SQL-based extraction, but it does not provide strong user-facing warnings about the sensitivity of returned data. In a cloud audit context, outputs may include asset inventories, IAM metadata, security configurations, and other information useful for reconnaissance or lateral movement.

Missing User Warnings

Low
Confidence
95% confidence
Finding
The code constructs an SQL statement by directly interpolating command-line inputs into the WHERE clause using f-strings. If an attacker can control provider, resource_type, or region_id, they may inject additional SQL conditions or alter query behavior, which is especially risky in a cloud resource audit tool that can enumerate sensitive asset metadata across environments.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.