Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-obs-statsgit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-obs-stats)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-obs-stats"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-obs-stats/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-obs-stats"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-obs-stats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 69 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 89 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 122 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- low Privilege Escalation · line 155 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00173 | $0.03740 |
| Opus 5.5 | $0.00069 | $0.01496 |
| Sonnet 5.5 | $0.00035 | $0.00748 |
| Haiku 4.5 | $0.00017 | $0.00374 |
Grade B, and why
huawei-cloud-obs-stats scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
> 1. **Stop immediately** - Do not execute any commands How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud OBS Statistics Skill
Overview
Query Huawei Cloud OBS (Object Storage Service) statistics: list buckets with capacity and object counts, query extranet/intranet download traffic with month-over-month comparison, and query total requests with month-over-month comparison.
⛔ Prohibited Operations (Security Constraints)
This skill strictly forbids the following delete operations, regardless of user requests:
| Prohibited Operation | API/Command | Reason |
|---|---|---|
| ❌ Delete bucket | DeleteBucket / obsutil rm -bucket |
Irreversible; destroys the entire bucket and all objects |
| ❌ Delete object | DeleteObject / obsutil rm |
Irreversible; deleted objects cannot be recovered (unless versioning is enabled) |
| ❌ Batch delete objects | DeleteObjects / obsutil rm -r |
Irreversible; batch deletion has a wide impact |
| ❌ Empty bucket | obsutil rm -bucket -r |
Irreversible; removes all objects in the bucket |
If a user requests a delete operation, you must refuse and inform: "Per security constraints, this skill does not allow delete operations (delete bucket/object/batch delete/empty bucket). Please use the Huawei Cloud OBS console or obsutil manually."
Architecture
Huawei Cloud OBS Statistics
├── ListBucketsWithStats (List buckets with capacity and object counts)
├── GetTraffic (Query extranet/intranet download traffic with MoM comparison)
└── GetRequests (Query total requests with MoM comparison)
Prerequisites
Prerequisite check 1/3: Huawei Cloud CLI (hcloud / KooCLI) >= 3.2.0 required Run
hcloud versionto verify version >= 3.2.0. If not installed or version is too low, see references/cli-installation-guide.md for installation guide.
hcloud version
Prerequisite check 2/3: obsutil >= 5.5.0 required (for OBS bucket listing) The hcloud OBS module uses obsutil under the hood. Bucket listing requires the obsutil CLI tool. Run
obsutil versionto verify version >= 5.5.0. If not installed, see references/cli-installation-guide.md for installation guide.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/acceptance-criteria.md 8.7 KB
- references/cli-installation-guide.md 6.0 KB
- references/iam-policies.md 4.5 KB
- references/obs-metrics.md 9.5 KB
- references/related-apis.md 11 KB
- references/task-list-buckets-with-stats.md 3.0 KB
- references/task-query-requests.md 4.1 KB
- references/task-query-traffic.md 5.1 KB
- references/troubleshooting.md 9.1 KB
- references/verification-method.md 7.2 KB
- scripts/obs_request_stats.py 13 KB runs code
- scripts/obs_traffic_stats.py 14 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 28d ago Changed 1ea6e1d34615
- 1mo ago First seen · 303 lines · 173 tokens per session scan B f85369a64075
huawei-cloud-obs-stats is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 3,740 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
huawei-cloud-apig-instance-management
Manage Huawei Cloud APIG (API Gateway, dedicated instances) via hcloud CLI: instance lifecycle (create/list/delete), API groups, API create/update/delete, publish/offline, request throttling policies, signature keys, access control (ACL) policies, and public ingress EIP binding, plus read-only diagnosis of public…
huawei-cloud-deployment-task-management
Huawei Cloud CloudDeploy (CodeArts Deploy / 部署) management, execution, and failure analysis using the KooCLI hcloud command-line client. Covers deploy application listing and creation, deployment task listing/detail/creation, task start, task deletion, deployment failure root-cause analysis (agent offline, timeout…
huawei-cloud-account-onboarding
A read-only helper for checking whether a Huawei Cloud account has completed real-name verification and guiding the user through phone-based face verification.
huawei-cloud-cost-estimation
A Huawei Cloud assistant for estimating resource prices, safely creating approved resources, and guiding users to unsubscribe through the Huawei Cloud console.
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…