Skills/ClawHub/huawei-cloud-waf-list

huawei-cloud-waf-list@1.0.3

VERIFIED

Publisher claims: "1. Query the list of Huawei Cloud WAF (Web Application Firewall, Web应用防火墙) protected websites / domain names under the current account through KooCLI (hcloud waf ListHost / ListCompositeHosts — read-only GET /v1/{project_id}/waf/instance and /v1/{project_id}/composite-waf/host). 2. Output modes: a compact table (default) with 防护域名 | 防护状态 | 接入方式 | 保活方式 | 独享IP | Domain ID key fields, --json (the raw host array)[, and --names-only (unique sorted domain list). 3. Supports --region to pick the region, --all-modes / --mode cloud|premium to select cloud-mode or dedicated/premium-mode protected domains, --hostname filtering, --protect-status (-1 bypass / 0 suspended / 1 enabled), --enterprise-project-id and --policyname filters, and automatic pagination (--pagesize, -1 = fetch all). Access mode (接入方式 cloud/premium) is surfaced from waf_type, keep-alive mode (保活方式) from proxy. 4. Explicit error hints for an empty protected-site list (「当前区域无 WAF 防护网站」), 403 / insufficient IAM permission (「无权限访问 WAF 防护网站列表」, WAF.00012006), disabled region (APIGW.0802), and hcloud not installed. 5. Built-in write-intent guard: any mutating intent (create / delete / update / migrate / rename / batch ...) is rejected before execution — this skill is strictly read-only. 6. Triggers include: "list WAF sites", "WAF 防护网站列表", "查询WAF防护域名", "WAF 域名列表", "WAF 防护状态查询", "WAF 网站盘点", "WAF 巡检", "list waf hosts", "waf protected domains", "华为云WAF列表". 7. Offline unit tests (mocked hcloud subprocess) cover routing, output modes, filters, error scenarios and the write-intent guard." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wlc-dev · joined 14 days agoInstalls 40Last detonated 1 h ago
$clawhub install huawei-cloud-waf-list
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-05 and scored it 88/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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

Static findings

MEDIUM
File permission modification commandscripts/ensure_cli.sh:96 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/ensure_cli.sh:93 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/install_cli.sh:80 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/install_cli.sh:83 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/list_waf_sites.py:63 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈2,784 tok
1 file · 12 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.

huawei-cloud-waf-list@1.0.3 safety verdict: Verified 88/100 — KillerSkills