CloudBase-AI-ToolkitBLOCK

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---name: ai-model-nodejsdescription: "Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration. The only SDK supporting image generation (ai.createImageModel + generateImage). Text via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*; model ids (e.g. deepseek-v4-flash, glm-5, kimi-k2.6) go in the `model` field of generateText/streamText. MUST run two-step preflight before code — see body. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat)."version: 2.34.4alwaysApply: false---## Sibling skills (local only)Sibling CloudBase skills ship beside this skill. Use local relative paths such as `../auth-tool-cloudbase/SKILL.md`.If a referenced sibling skill file is missing from this environment, ask the user to install the full CloudBase plugin (or the missing skill). Do **not** HTTP-fetch remote skill or protocol markdown into the agent context.## When to use this skillUse this skill for **calling AI models from Node.js backends, cloud functions, or CloudRun services** via `@cloudbase/node-sdk`.> 🧭 **Runtime-plane fit.** This is the right skill when the AI call truly belongs on the server: image generation (the only SDK that supports it), long-running agent jobs, orchestration across multiple tools, scheduled tasks, or flows that must keep secrets server-side. **If the user is building a Web page / frontend AI chat UI, do NOT wrap this SDK behind a backend proxy** — route to `ai-model-web` and call the model directly from the browser. For WeChat Mini Programs use `ai-model-wechat`. Routing is decided by runtime plane first; the concrete model (`deepseek-*`, `glm-*`, `hunyuan-*`, `kimi-*`, ...) only affects the `model` field.**Use it when you need to:**- Integrate AI text generation into a backend service- Generate images with the Hunyuan Image model- Call AI models from CloudBase cloud functions or CloudRun- Do server-side AI processing (agent orchestration, batch jobs, scheduled tasks)**Do NOT use for:**- Browser/Web apps → use the `ai-model-web` skill- WeChat Mini Program → use the `ai-model-wechat` skill- Runtimes without a CloudBase SDK (Python, Go, PHP, curl, etc.) → use the `http-api-cloudbase` skill (it now includes the `ai_model` OpenAPI spec for direct HTTP calls to the AI model endpoint; do NOT wrap this SDK behind an HTTP proxy)---## ⛔ STOP — `ai.createModel(...)` argument is **not** a vendor / model nameRead this before writing any `createModel(...)` line. Agents frequently hallucinate this argument. There are **exactly three** legal shapes. Anything else is a bug.| ✅ Legal `ai.createModel(...)` argument | When to use it ||----------------------------------------|----------------|| `"cloudbase"` | **The main managed group for server-side projects** (TokenHub-backed, multi-vendor pool). Vendor + concrete model go into the **`model` field** of `generateText` / `streamText`, e.g. `{ model: "deepseek-v4-flash" }`. **No model is enabled by default — always check `DescribeAIModels` first and, if the target model is missing, enable it with `UpdateAIModel` before calling the SDK.** || `"hunyuan-exp"` | Only if `DescribeAIModels` explicitly returns this legacy builtin group for the current env. || `"custom-<your-name>"` | A user-defined GroupName you onboarded via `CreateAIModel`. **Must** start with `custom-` (e.g. `custom-kimi`, `custom-openai-compat`). |> Image generation is a separate entry point: `ai.createImageModel("hunyuan-image")`. Do not mix it with `createModel(...)`.### ❌ Wrong argument patternsAnything that is not one of the three legal values above: vendor names (`"deepseek"`, `"glm"`, `"kimi"`, `"openai"`, `"moonshot"`, ...), concrete model ids (`"deepseek-v4-flash"`, `"hunyuan-2.0-instruct-20251111"`), the bare placeholder `"custom"`, or a variable holding the model id. All of these are bugs in `createModel(...)`.### ✅ Correct pattern — GroupName vs Model are two different fields```jsconst model = ai.createModel("cloudbase");          // ← GroupNameawait model.generateText({  model: "deepseek-v4-flash",                       // ← concrete model id  messages: [...]});```### Decision procedure (when the user names a specific model)1. The user says "use DeepSeek v3.2" / "use hunyuan instruct" / "use Kimi k2.6" / "use GLM-5" / ...2. `createModel("cloudbase")` stays the same.3. Put the model id into the **`model` field**: `{ model: "deepseek-v3.2" }`, `{ model: "hunyuan-2.0-instruct-20251111" }`, `{ model: "kimi-k2.6" }`, `{ model: "glm-5" }`, ...4. **Never assume the model is already enabled.** Before calling the SDK, verify it is present in `DescribeAIModels({ GroupName: "cloudbase" }).Models[]`. If missing, call `DescribeManagedAIModelList` to confirm the exact `Model` name the platform supports (case-sensitive — do **not** guess the spelling) and then enable it via `UpdateAIModel` with `Status: 1` (remember `Models` is a full replacement).> If you are about to type `ai.createModel(` and the thing inside the parentheses is a vendor name, a model name, or a guess — **stop**. It is almost certainly one of the three legal values above.---## Mandatory Two-Step Preflight (before any SDK code)Before calling any AI API on the server, **run the two-step preflight**: 1 eligibility, 2 group readiness. **Text generation and image generation draw from the same Token Credits resource pack**, and both must complete the preflight before code is emitted.### Step 0: obtain the environment IDCall the MCP tool `queryEnv` with `action=info` and read `EnvId` from the response.---### Preflight 1 — Eligibility (Token Credits resource pack)Call the MCP tool:```callCloudApi(service="tcb", action="DescribeEnvPostpayPackage", params={ EnvId })```**Pass conditions (all required):**- `envPostpayPackageInfoList` contains at least one entry- That entry's `postpayPackageId` starts with `pkg_tcb_tokencredits_`- That entry's `status` is NOT in `

BLOCKgrade F · trust 23/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

What the source does

Filesystem

declared (5 observation(s))

Network

declared (10 observation(s))

Shell

declared (11 observation(s))

Dependencies

not all pinned

Secrets in source

found

Findings (25)

1. **Run the two-step preflight before writing business code** — 1 eligibility: `queryEnv` → `callCloudApi(tcb, DescribeEnvPostpayPackage)` to confirm the Token Credits resource pack (text + image sha

1. **Run the two-step preflight before writing business code** — 1 eligibility: `queryEnv` → `callCloudApi(tcb, DescribeEnvPostpayPackage)` to confirm the Token Credits resource pack (text + image sha

const data = yaml.load(yamlContent) as { scenarios?: Record<string, any>[] };

frontmatter: yaml.load(match[1]) || {},

const config = yaml.load(fs.readFileSync(CONFIG_FILE, 'utf8'));

const config = yaml.load(configContent);

frontmatter = yaml.load(frontmatterText) || {};

exec(`git clone --depth 1 --branch ${ref} ${repo} ${tmpDir}`, {

"metadata.google.internal",

> - **Enabling / configuring login providers** (phone SMS, email, WeChat Open Platform, username+password, OAuth, ...) → follow the **`auth-tool-cloudbase`** skill (backend config via `callCloudApi`).

- Read the current credential scope from `auth` tools: `credential_scope: account` = account-level, reaches control-plane APIs subject to that identity's CAM policies; `env` = API Key, scoped to one e

3. **Understand PG roles before writing code:** Publishable Key maps to `anon`; a logged-in user's access token maps to `authenticated`; API Key maps to `service_role` and bypasses RLS. Never expose A

When `wait=false` returns a `taskId`, the deployment workflow is not complete. Automatically call `queryFunctions` with `action="getFunctionDeployStatus"` and that `taskId`; continue while the status 

When `wait=false` returns a `taskId`, the deployment workflow is not complete. Automatically call `queryFunctions` with `action="getFunctionDeployStatus"` and that `taskId`; continue while the status 

When `wait=false` returns a `taskId`, the deployment workflow is not complete. Automatically call `queryFunctions` with `action="getFunctionDeployStatus"` and that `taskId`; continue while the status 

When `wait=false` returns a `taskId`, the deployment workflow is not complete. Automatically call `queryFunctions` with `action="getFunctionDeployStatus"` and that `taskId`; continue while the status 

.DS_Store

.DS_Store

.agents/skills/api-contract-review

.agents/skills/cloud-api-recipe-authoring

.agents/skills/codebuddy-ide-mcp-upgrade

.agents/skills/doc-freshness-review

.agents/skills/docs-workflows

await this.postFetch('https://otheve.beacon.qq.com/analytics/v2_upload', payload);

var BEACON_UPLOAD_URL = "https://otheve.beacon.qq.com/analytics/v2_upload";

Gates applied: critical_finding, instruction_override, no_behavioural_pass, undeclared_transfer.