The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess.run in scripts/hcloud_executor.py to execute the Huawei Cloud CLI (hcloud). The commands are constructed using shell=False, which is a security best practice to prevent shell injection by ensuring arguments are not interpreted by a shell. The command set is limited to read-only queries as described in the skill's core workflow.
[EXTERNAL_DOWNLOADS]: The documentation in references/cli-installation-guide.md includes instructions to download and execute the official Huawei Cloud CLI installation script using a curl | bash pattern. The download source is https://cn-north-4-hdn-koocli.obs.cn-north-4.myhuaweicloud.com, which is an official vendor domain. As the skill is authored by the vendor and points to its own official resources, this is considered a standard deployment procedure.
[INDIRECT_PROMPT_INJECTION]: The skill processes cloud resource metadata and monitoring metrics retrieved from Huawei Cloud APIs. While this constitutes an ingestion surface for untrusted external data, the skill does not interpolate this data back into instructions or prompts for the LLM; instead, it formats the data into a local, offline-capable HTML report, significantly reducing the risk of a successful injection attack.

huawei-cloud-ces-drill-inspection