Skills/ClawHub/huawei-cloud-gaussdb-list

huawei-cloud-gaussdb-list@1.0.1

VERIFIED· install only

Publisher claims: "1. List Huawei Cloud GaussDB (云数据库 GaussDB for MySQL) instances in a tenant region through KooCLI (`hcloud GaussDB ListGaussMySqlInstances`, the official read-only GET /v3/{project_id}/instances), with an automatic fallback to the official `huaweicloudsdkgaussdb` v3 SDK (`GaussDBClient.list_gauss_my_sql_instances`) when KooCLI is not installed. 2. Default output is an aligned Chinese-header table (名称/实例ID/状态/引擎/引擎版本/规格/CPU内存/存储类型/存储/私网IP/公网IP/ 端口/类型/区域/VPC/子网/创建时间); `--json` prints the raw instance array; `--format md` / `-o FILE` exports the same fields as a Markdown table file (default `gaussdb_instances_<region>_<timestamp>.md`). 3. Supports `--region` override (default cn-north-4), `--name` server-side fuzzy filtering (a leading `*` is added when missing), `--status` client-side exact filtering (the real API has no status parameter), and automatic `limit`/`offset` paging until the reported total is reached. 4. Ambiguous / empty results are explained explicitly: 「当前区域（<x>）无 GaussDB 实例」, 403 / insufficient IAM permission, missing AK/SK credentials, and network / API failures. 5. Built-in write-intent guard: any mutating intent (create / delete / update / resize / restart / stop / backup / restore / bind / unbind ...) or any operation other than `ListGaussMySqlInstances` is rejected before a single command runs — this skill is strictly read-only. 6. Triggers include: "查询 GaussDB 实例列表", "GaussDB 实例列表", "GaussDB inventory", "list GaussDB instances", "华为云 GaussDB 实例", "GaussDB MySQL 实例清单", "查询云数据库 GaussDB 实例", "GaussDB list"." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wlc-dev · publishing for 30 daysInstalls 51Last detonated 5d ago
$clawhub install huawei-cloud-gaussdb-list
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 91/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/list_gaussdb.py:302 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

No other findings across 1,297 lines in 8 files.

Cost to the agent

Instructions loaded
≈3,805 tok
1 file · 8 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.