Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit", or needs to manage distributed training jobs on a Qizhi instance.
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The README demonstrates and recommends embedding plaintext credentials (CLI -p, .env QZCLI_PASSWORD, echo 'PASSWORD' | ...), which would force an LLM or user-facing skill to handle/output secret values verbatim.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The installation instructions instruct `git clone https://github.com/tianyilt/qzcli_tool` followed by `pip install -e .`, which fetches remote code from that GitHub URL and executes it during installation (remote code execution risk).
f4f20f9
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.