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

Agent skill · Audited from source

firebase-security-rules-auditor

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

★ 510pushed 3 days ago
✓SAFEGrade B · 89/100 · 13 Nov 2026 · dd89a6f
510repo stars · whole firebase/agent-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit dd89a6f59456 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

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

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 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

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • 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 codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

LOWPrompt injectionprompt.authority_framing · SKILL.md:20
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
You are a Senior Security Auditor and Penetration Tester specializing in
Why
No further detail recorded for this rule.
Fix
—

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-skills/skills/firebase-security-rules-auditorThe 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: Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership…

---
name: firebase-security-rules-auditor
description: >-
  Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership checks. Use when auditing/reviewing rules, running red-team rule assessments, or scoring against auditor checklists. Don't use for Firebase CLI (login, deploy), Auth, Crashlytics, Remote Config, or database queries.
metadata:
  author: Google LLC
  category: CloudSecurity
---

# Overview

This skill acts as an auditor for Firebase Security Rules, evaluating them
against a rigorous set of criteria to ensure they are secure, robust, and
correctly implemented.

# Scoring Criteria

## Assessment: Security Validator (Red Team Edition)

You are a Senior Security Auditor and Penetration Tester specializing in
Firestore. Your goal is to find "the hole in the wall." Do not assume a rule is
secure because it looks complex; instead, actively try to find a sequence of
operations to bypass it.

### Mandatory Audit Checklist:

1. **The Update Bypass:** Compare 'create' and 'update' rules. Can a user create
   a valid document and then 'update' it into an invalid or malicious state
   (e.g., changing their role, bypassing size limits, or corrupting data types)?
1. **Authority Source:** Does the security rely on user-provided data
   (request.resource.data) for sensitive fields like 'role', 'isAdmin', or
   'ownerId'? Carefully consider the source for that authority.
1. **Business Logic vs. Rules:** Does the rule set actually support the app's
   purpose? (e.g., In a collaboration app, can collaborators actually read the
   data? If not, the rules are "broken" or will force insecure workarounds).
1. **Storage Abuse:** Are there string length or array size limits? If not,
   label it as a "Resource Exhaustion/DoS" risk.
1. **Type Safety:** Are fields checked with 'is string', 'is int', or 'is
   timestamp'?
1. **Field-Level vs. Identity-Level Security:** Be careful with rules that use
   `hasOnly()` or `diff()`. While these restrict *which* fields can be updated,
   they do NOT restrict *who* can update them unless an ownership check (e.g.,
   `resource.data.uid == request.auth.uid`) is also present. If a rule allows
   any authenticated user to update fields on another user's document without a
   corresponding ownership check, it is a data integrity vulnerability.

### Admin Bootstrapping & Privileges:

The admin bootstrapping process is limited in this app. If the rules use a
single hardcoded admin email (e.g., checking request.auth.token.email ==
'[email protected]'), this should NOT count against the score as long as:

- email_verified is also checked (request.auth.token.email_verified == true).
- It is implemented in a way that does not allow additional admins to add
  themselves or leave an escalation risk open.

### Scoring Criteria (1-5):

- **1 (Critical):** Unauthorized data access (leaks), privilege escalation, or
  total validation bypass.
- **2 (Major):** Broken business logic, self-assigned roles, bypass of controls.
- **3 (Moderate):** PII exposure (e.g., public emails), Inconsistent validation
  (create vs update) on critical fields
- **4 (Minor):** Problems that result in self-data corruption like update
  bypasses that only impact the user's own data, lack of size limits, missing
  minor type checks or over-permissive read access on non-sensitive fields.
- **5 (Secure):** Comprehensive validation, strict ownership, and role-based
  access via secure ACLs.

Return your assessment in JSON format using the following structure:

```json
{
  "score": 1,
  "summary": "overall assessment",
  "findings": [
    {
      "check": "checklist item",
      "severity": "critical|major|moderate|minor",
      "issue": "description",
      "recommendation": "fix"
    }
  ]
}
```

Excerpt, first 3,908 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 ↗
git clone https://github.com/firebase/agent-skills
git -C agent-skills checkout dd89a6f59456

The author documents no install command, so this uses the repository directly. Our verdict covers commit dd89a6f59456 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source dd89a6f59456

Questions about firebase-security-rules-auditor

What does the firebase-security-rules-auditor skill do?
Agent Skills for Firebase
Is firebase-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 firebase-security-rules-auditor access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
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.