What is huaweicloud-safety?

A safety guide for Huawei Cloud work involving credentials, cloud resources, access control, public exposure, or costs.

Classifying cloud operations, reviewing planned changes, redacting sensitive output, and safely handling Huawei Cloud commands.

It prevents secrets from being exposed and requires approval before actions that could change resources, security, billing, or network access.

huaweicloud-safety — Skill for Codex by huaweicloud

Install

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.

Any agent

npx skills add huaweicloud/huaweicloud-devkit --skill huaweicloud-safety

Clone the repo

git clone --depth 1 https://github.com/huaweicloud/huaweicloud-devkit

Made for: Codex.

Or install huaweicloud-devkit, the plugin that ships this one along with the rest of its 27 skills, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-devkit/huaweicloud-safety/github.svg)](https://agentmods.dev/skills/huaweicloud/huaweicloud-devkit/huaweicloud-safety)

Your own site

<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-devkit/huaweicloud-safety"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-devkit/huaweicloud-safety/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-devkit/huaweicloud-safety"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-devkit/huaweicloud-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 766 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, 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 14
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.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00048	$0.00766
Opus 5	$0.00024	$0.00383
Sonnet 5	$0.00010	$0.00153
Haiku 4.5	$0.00005	$0.00077

Measured 2d ago against content hash efb6026a07fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

huaweicloud-safety scanned grade A with 0 findings 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/huaweicloud-core/skills/huaweicloud-safety/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Huawei Cloud Safety

STOP - Do not answer from general knowledge. Follow the procedure below.

Use this skill before any Huawei Cloud action that may expose secrets, change resources, affect cost, change IAM, or expose a network endpoint.

Rules

Never ask the user to paste AK/SK, SK, tokens, passwords, private keys, or credential files.
Never read local .hcloud or .huaweicloud credential files into the agent context.
Never call APIs or CLI operations that return secret values directly into the agent context.
Always classify operations before execution:
- read-only
- write
- secret
- IAM/security
- cost/payment
- public exposure
For any non-read-only operation, show the exact planned change and wait for explicit user approval.
Redact secrets from command output, errors, JSON, logs, and generated reports.
If a command contains adminPass, password, token, or any secret-like field, warn that plaintext can remain in shell history. Prefer local-only input, runtime injection, or user-side execution.

Enforcement Layers

Hooks: hooks/huaweicloud-safety.mjs blocks risky Codex native hook calls without requiring Python; hooks/huaweicloud-safety.py remains for Hermes/Python hook compatibility.
MCP wrapper: the Node MCP server applies the same safety policy for Codex/OpenCode paths that do not enforce hooks.
Skills: this document teaches agents the rule before they act.

Write Execution Boundary

Default path: use huaweicloud_plan_cli_command to produce a reviewed command block, then let the user or host agent execute it after approval.
Approved tool path: use huaweicloud_run_approved_command only when the exact planned command has been shown and the user explicitly approved that exact command.
After a write, verify with huaweicloud_run_readonly_command or another read-only check.

Proactive Hook Checks

Before executing, deploying, or handing generated cloud artifacts to the user, run the matching check when available:

Read the full file on GitHub · 60 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 209 B

Changes

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.

2d ago Changed efb6026a07fb
12d ago First seen · 60 lines · 48 tokens per session scan A 82971443b8ca

Subscribe to this mod's changes

huaweicloud-safety is a skill published in the GitHub repository huaweicloud/huaweicloud-devkit (47 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 766 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Cloud DevOps and cloud Security ai-coding api cli huaweicloud sdk terraform

fastapi

Use when building, reviewing, testing, securing or shipping a FastAPI / async Python service — routers, Pydantic v2 schemas, dependency injection, async SQLAlchemy 2.0, OAuth2/JWT, ASGITransport tests, production wiring. NOT language-level Python or packaging (that is python), NOT engine-level SQL (that is…

ericrisco/rsc-harness · 94 tokens

aws-essentials

Use when standing up the core AWS surface a small product needs: hardening a fresh account, a private S3 bucket, encrypted RDS Postgres, ECS Fargate vs EC2, CloudFront + OAC, or scoping an IAM policy to least privilege. NOT the CI pipeline that ships the container (that is deployment), NOT app-code access-control…

ericrisco/rsc-harness · 89 tokens

fly-io

Use when deploying or operating an app on Fly.io — writing fly.toml, placing Machines in regions near users, attaching Volumes, managing secrets, or picking a scaling lever (autostop/autostart, scale count, fly-replay). NOT choosing which host to deploy on (that is deployment), NOT a git-push PaaS with no regions…

ericrisco/rsc-harness · 87 tokens

netlify

Use when deploying or operating a site on Netlify — writing or fixing netlify.toml, authoring Functions or Edge Functions, redirects, rewrites and headers, env vars per deploy context, and shipping via the Netlify CLI. NOT deploying to Vercel (that is vercel).

ericrisco/rsc-harness · 63 tokens

frontmcp-deployment

Use when deploying, building for production, packaging, or shipping a FrontMCP server. Covers build targets (node, cli SEA binary, browser, embeddable SDK, mcpb archive for Claude Desktop, serverless) and deploying to Vercel (with Vercel KV), AWS Lambda (API Gateway, SAM, CDK), Cloudflare Workers (KV, D1, Durable…

agentfront/frontmcp · 210 tokens

huawei-cloud-solution-ops

A skill for Huawei Cloud solution operations. It helps agents inspect, plan, operate, troubleshoot, and verify Huawei Cloud resources through hcloud, Huawei Cloud SDKs, Terraform, and MaaS capabilities. Use this when users want to query or change Huawei Cloud resources, troubleshoot authentication and API issues…

huaweicloud/huaweicloud-skills · 81 tokens