huawei-cloud-cc-central-network-query

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions in references/cli-installation-guide.md to download the hcloud CLI installation script from the official Huawei Cloud support domain (support.huaweicloud.com). This is a standard procedure for setting up the required environment.
  • [COMMAND_EXECUTION]: The skill utilizes the hcloud command-line interface to execute GET requests against the Huawei Cloud API. All documented commands are restricted to read-only operations (List and Show), minimizing the risk of accidental or malicious modifications to cloud infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes structured JSON data returned from the Huawei Cloud API, such as resource IDs and names, which are then used as parameters for subsequent CLI commands.
  • Ingestion points: Data retrieved from ListCentralNetworks, ListCentralNetworkAttachments, and ListCentralNetworkConnections enters the agent context.
  • Boundary markers: Commands use structured parameter flags (e.g., --central_network_id=) to separate data from the command structure.
  • Capability inventory: Subprocess calls are limited to the hcloud CLI and a JSON parsing command using python3 in the provided test script.
  • Sanitization: The skill assumes the integrity of the cloud provider's API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 08:45 AM
Security Audit — agent-trust-hub — huawei-cloud-cc-central-network-query