Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

firestore-security-rules-auditor

skill · firebase/agent-skillsApache-2.0 licenceAudited 13 Nov 2026 · source dd89a6f59456

★ 511pushed 3 days agoversion 1.0.0
✓SAFEGrade B · 89/100 · 13 Nov 2026 · dd89a6f
511repo stars · whole firebase/agent-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit dd89a6f59456 and observed filesystem and shell access and no hard-coded secrets. What it does: Skill for converting an installed Firebase Extension (or extension source) into a standalone Cloud Functions for Firebase codebase or publishable npm package, including V1 to V2 trigger upgrades, lifecycle hooks, and…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “firestore-security-rules-auditor (firebase/agent-skills)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/firebase/firestore-security-rules-auditor

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium13 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemDeclared1 observation
  • NetworkNone observedNo outbound calls in the source
  • ShellDeclared4 observations
  • DependenciesNot pinnedSome versions float
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS2
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS11
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (13)

LOWFilesystem / pathfs.traversal · scripts/skill-token-counter/index.js:193
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const targetParam = targetParams[0] || '../../skills';
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainsupply.unpinned · scripts/skill-token-counter/package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
@google/generative-ai
Why
1 dependency range(s) float
Fix
pin exact versions or ship a lockfile
LOWPrompt injectionprompt.authority_framing · skills/firebase-data-connect-basics/reference/cloud_functions.md:110
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
| **Admin SDK (Full privileges)**      | `"admin"`           | Empty                                            |
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.authority_framing · skills/firebase-data-connect-basics/reference/sdk_admin_node.md:4
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
needs elevated privileges or needs to impersonate specific users.
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.authority_framing · skills/firebase-data-connect-basics/reference/sdk_admin_node.md:12
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- **Follow Least Privilege**: Admin SDKs have unrestricted access by default.
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.authority_framing · skills/firebase-data-connect-basics/reference/sdk_admin_node.md:22
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
can only be called via the Admin SDK with unrestricted access.
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.authority_framing · skills/firebase-data-connect-basics/reference/sdk_admin_node.md:129
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
#### 4. Running with Unrestricted Access
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.credential_read · skills/firebase-ai-logic-basics/references/usage_patterns_web.md:264
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
// ✅ SAFE: Load dynamically from Vite environment variable; fallback to true to auto-generate
Why
asks the agent to read credentials
Fix
—
LOWPrompt injectionprompt.credential_read · skills/firebase-basics/references/web_setup.md:119
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
// ✅ SAFE: Load dynamically from Vite environment variable; fallback to true to auto-generate
Why
asks the agent to read credentials
Fix
—
LOWPrompt injectionprompt.persistence · skills/firebase-basics/references/flutter_setup.md:18
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
1. **Update PATH**: Add the `bin` folder to your shell configuration (e.g.,
Why
instructs the agent to persist itself in the user's environment
Fix
—
LOWPrompt injectionprompt.transfer_instruction · skills/firebase-data-connect-basics/reference/security.md:79
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
@auth(expr: "auth.token.email_verified && auth.token.email.endsWith('@company.com')")
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine
LOWPrompt injectionprompt.transfer_instruction · skills/firebase-data-connect-basics/reference/security.md:286
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
@auth(expr: "auth.token.email.endsWith('@company.com')")
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine
LOWPrompt injectionprompt.transfer_instruction · skills/firebase-data-connect-basics/reference/security.md:289
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
@auth(expr: "auth.token.email_verified && auth.token.email.endsWith('@company.com')")
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine

Audit 0.4.1 · source sha dd89a6f59456 · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherfirebase GitHub organizationOwner of the repository this skill is read from
  • Source folderfirebase/agent-skillsThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdictdd89a6f59456A new audit runs when the source changes
  • Repository statusNot archivedLast push 3 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Skill for converting an installed Firebase Extension (or extension source) into a standalone Cloud Functions for Firebase codebase or publishable npm package, including V1 to V2 trigger upgrades, lifecycle hooks, and…

---
name: extension-to-functions-codebase
description: Skill for converting an installed Firebase Extension (or extension source) into a standalone Cloud Functions for Firebase codebase or publishable npm package, including V1 to V2 trigger upgrades, lifecycle hooks, and declarative security
metadata:
  author: Google LLC
  category: Serverless
---

# Extension to Functions Codebase & npm Package Migration

## Overview

Migrates a Firebase Extension into either:

1. **A local Cloud Functions codebase** (`functions/src/` for app integration).
1. **A publishable npm package** (reusable open-source package exporting V2
   functions).

Leverages native Cloud Functions features (declarative IAM, Parameterized
Config, SDK Lifecycle Hooks) and modernizes 1st Gen triggers to 2nd Gen using
the Destructuring Compatibility Shim.

______________________________________________________________________

## Target Migration Workflows

- **Target A: Local Functions Codebase** (End-User App Integration)

  - Output: Code under `functions/src/`. Config in `.env`.
  - Deployment: `firebase deploy --only functions`.

- **Target B: Publishable npm Package / Shareable Package**

  - Output: Reusable npm package exporting V2 functions.
  - Configuration: `package.json` specifying `exports` map,
    `engines: { "node": ">=22" }`, and
    `peerDependencies: { "firebase-functions": ">=6.0.0" }`.
  - Usage: Consumers install package and re-export functions in `index.ts`
    (`export * from "<package-name>"`).

______________________________________________________________________

## Core Rules & Constraints

### 1. Declarative IAM & APIs (Zero-Local-Overhead)

Use native SDK declarations instead of manual `gcloud` scripts or console
instructions:

- Use `requiresRole("roles/...")` for required GCP IAM permissions.
- Use `requiresAPI("service.googleapis.com", "Description")` for Google APIs.

### 2. Global Parameter Access Restriction

- **Never call `.value()` at top-level module load scope.**
- Initialize global SDK instances inside `onInit()` or lazy getters:
  ```typescript
  import { defineString } from "firebase-functions/params";
  import { onInit } from "firebase-functions/v2";

  const dataset = defineString("DATASET_ID");
  let client: BigQuery;

  onInit(() => {
    client = new BigQuery({ datasetId: dataset.value() });
  });
  ```

### 3. V2 Concurrency & Cost Parity

V2 enables concurrency (up to 80 requests). To preserve V1 single-concurrency
pricing, set `cpu: "gcf_gen1"`.

______________________________________________________________________

## Step-by-Step Migration Execution

### Step 1: Inventory Extension Resources

1. **`extension.yaml`**:
   - `params` → `defineString`, `defineInt`, `defineBoolean`, `defineSecret`.
   - `apis` → `requiresAPI(...)`.
   - `roles` → `requiresRole(...)`.
   - `lifecycleEvents` → `afterFirstDeploy` & `afterRedeploy`.
   - `resources` → Upgrade 1st Gen triggers to 2nd Gen (`onDocumentWritten`,
     `onTaskDispatched`, `onRequest`).
1. **Files & Scripts**: Preserve devDependencies, test framework (`jest`), and
   test scripts.

### Step 2: Configure `package.json`

- Set `name: "<package-name>"`, `engines: { "node": ">=22" }`.
- Set `peerDependencies`:
  ```json
  "peerDependencies": {
    "firebase-admin": "^11.0.0 || ^12.0.0",
    "firebase-functions": ">=6.0.0"
  }
  ```
- Configure `exports` map targeting ESM/CommonJS and TypeScript declarations
  (`lib/index.js`, `lib/index.d.ts`).

### Step 3: Upgrade Triggers from V1 to V2

- Firestore: Use `onDocumentWritten` from `firebase-functions/v2/firestore`.
- Tasks: Use `onTaskDispatched` from `firebase-functions/v2/tasks`. Remove
  `EXT_INSTANCE_ID` when enqueueing tasks.
- HTTP: Use `onRequest` from `firebase-functions/v2/https`.
- Apply Destructuring Compatibility Shim (`{ change, context }`,
  `{ snapshot, context }`) where legacy 1st Gen handlers expect
  `(change, context)`.

### Step 4: Convert Lifecycle Events

Map extension lifecycle events to SDK lifecycle hooks in `src/index.ts`:

- `onInstall` → `afterFirstDeploy({ task: { function: "initTask" } })`
- `onUpdate` / `onConfigure` →
  `afterRedeploy({ task: { function: "setupTask" } })`

### Step 5: Package README & Export Instructions

Generate `README.md` containing:

1. Installation instructions (`npm install`).
1. Re-export snippet (`export * from "<package-name>"`).
1. Parameterized Configuration `.env` reference table.
1. What Changed (Extension vs Package) comparison table.

_Reminder: NEVER execute `npm publish`._

Excerpt, first 4,537 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit dd89a6f

Download folder ↗
npx skills add  https://github.com/firebase/skills/tree/<branch-name>
npx skills add firebase/skills
claude plugin install firebase@firebase
git clone https://github.com/firebase/skills.git
npx skills add /path/to/your/local/firebase-skills/skills
npx skills add

Commands as the repository documents them: shown, never run by us. Our verdict covers commit dd89a6f59456 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
Claude DesktopMentioned in its text, not testedSkills for Claude Desktop · About Claude Desktop
CodexMentioned in its text, not testedSkills for Codex · About Codex
GitHub CopilotMentioned in its text, not testedSkills for GitHub Copilot · About GitHub Copilot
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
Gemini CLIMentioned in its text, not testedSkills for Gemini CLI · About Gemini CLI
WindsurfMentioned in its text, not testedSkills for Windsurf · About Windsurf
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source dd89a6f59456

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/firebase/firestore-security-rules-auditor/badge.svg)](https://modelsatlas.com/skills/firebase/firestore-security-rules-auditor/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/firebase/firestore-security-rules-auditor/badge.svg)](https://modelsatlas.com/skills/firebase/firestore-security-rules-auditor/)

Questions about firestore-security-rules-auditor

What does the firestore-security-rules-auditor skill do?
Agent Skills for Firebase
Is firestore-security-rules-auditor safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can firestore-security-rules-auditor access on my machine?
The audit observed that it runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does firestore-security-rules-auditor work with?
Its documentation mentions claude-code, claude-desktop, codex, copilot, cursor, gemini-cli and windsurf. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (dd89a6f59456), read on 2026-11-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.